Curation by Talkstation 10 months, 3 weeks ago for query arxiv
Original results
-
https://arxiv.org/ — found via Mwmbl
arXiv.org e-Print archive
arXiv is a free distribution service and an open-access archive for 2,183,548 scholarly articles in the fields of physics, mathematics, computer science, …
-
http://arxiv.org/abs/1411.4389 — found via Mwmbl
[1411.4389] Long-term Recurrent Convolutional Networks for Visua…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1205.2024 — found via Mwmbl
[1205.2024] Quantum teleportation and entanglement distribution …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1205.3909 — found via Mwmbl
[1205.3909] Quantum teleportation using active feed-forward betw…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/0811.2251 — found via Mwmbl
[0811.2251] The endpoint case of the Bennett-Carbery-Tao multili…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/0705.3773 — found via Mwmbl
[0705.3773] Circular law, Extreme Singular values and Potential …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1103.2759 — found via Mwmbl
[1103.2759] Quiver varieties and the character ring of general l…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=88 — found via Mwmbl
Cellphone records reveal new patterns of human activity « the ph…
Switch yer mobile phone on and it checks into the local network giving your location and the time you were there. The network also records the calls you m…
-
https://arxiv.org/abs/1312.6114 — found via Mwmbl
[1312.6114] Auto-Encoding Variational Bayes
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1307.2196 — found via Mwmbl
[1307.2196] Neural Dust: An Ultrasonic, Low Power Solution for C…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1609.03528 — found via Mwmbl
[1609.03528] The Microsoft 2016 Conversational Speech Recognitio…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1507.06947 — found via Mwmbl
[1507.06947] Fast and Accurate Recurrent Neural Network Acoustic…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/0809.2579 — found via Mwmbl
[0809.2579] Exercises in the birational geometry of algebraic va…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1606.08954 — found via Mwmbl
[1606.08954] Greedy, Joint Syntactic-Semantic Parsing with Stack…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=596 — found via Mwmbl
Do nuclear decay rates depend on our distance from the sun? « th…
We think that the decay rates of elements are constant regardless of the ambient conditions (except in a few special cases where beta decay can be influen…
-
http://arxivblog.com/?p=370 — found via Mwmbl
Quantum zeno effect explains bird navigation « the physics arXi…
Quantum zeno effect explains bird navigation Just how birds use the earth’s magnetic field to navigate has puzzled researchers for decades. But in recent…
-
http://arxivblog.com/?p=664 — found via Mwmbl
The neglected puzzle of low energy nuclear reactions « the physi…
Cold fusion won’t go away and perhaps rightly so. Numerous groups have reported idiosyncratic behaviour of palladium hydrides sitting in heavy water when …
-
https://arxiv.org/abs/1810.04805 — found via Mwmbl
[1810.04805] BERT: Pre-training of Deep Bidirectional Transforme…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1707.06347 — found via Mwmbl
[1707.06347] Proximal Policy Optimization Algorithms
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1705.08807 — found via Mwmbl
[1705.08807] When Will AI Exceed Human Performance? Evidence fro…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1812.04948 — found via Mwmbl
[1812.04948] A Style-Based Generator Architecture for Generative…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2311.15421 — found via Mwmbl
[2311.15421] Wired Perspectives: Multi-View Wire Art Embraces Ge…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1712.00409 — found via Mwmbl
[1712.00409] Deep Learning Scaling is Predictable, Empirically
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1906.02825 — found via Mwmbl
[1906.02825] XRAI: Better Attributions Through Regions
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1810.08575 — found via Mwmbl
[1810.08575] Supervising strong learners by amplifying weak expe…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2002.11667 — found via Mwmbl
[2002.11667] An inverse theorem for Freiman multi-homomorphisms
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1905.12616 — found via Mwmbl
[1905.12616] Defending Against Neural Fake News
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1705.08417 — found via Mwmbl
[1705.08417] Reinforcement Learning with a Corrupted Reward Chan…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2107.03374 — found via Mwmbl
[2107.03374] Evaluating Large Language Models Trained on Code
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1906.08237 — found via Mwmbl
[1906.08237] XLNet: Generalized Autoregressive Pretraining for L…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1707.03497 — found via Mwmbl
[1707.03497] Value Prediction Network
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1911.09070 — found via Mwmbl
[1911.09070] EfficientDet: Scalable and Efficient Object Detecti…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1510.03055 — found via Mwmbl
[1510.03055] A Diversity-Promoting Objective Function for Neural…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1707.08945 — found via Mwmbl
[1707.08945] Robust Physical-World Attacks on Deep Learning Mode…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1802.01548 — found via Mwmbl
[1802.01548] Regularized Evolution for Image Classifier Architec…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1803.11175 — found via Mwmbl
[1803.11175] Universal Sentence Encoder
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1612.03801 — found via Mwmbl
[1612.03801] DeepMind Lab
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1710.09437 — found via Mwmbl
[1710.09437] Casper the Friendly Finality Gadget
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1611.01224 — found via Mwmbl
[1611.01224] Sample Efficient Actor-Critic with Experience Replay
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2103.03874 — found via Mwmbl
[2103.03874] Measuring Mathematical Problem Solving With the MAT…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1704.03477 — found via Mwmbl
[1704.03477] A Neural Representation of Sketch Drawings
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1804.08199 — found via Mwmbl
[1804.08199] Linguistically-Informed Self-Attention for Semantic…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2203.11171 — found via Mwmbl
[2203.11171] Self-Consistency Improves Chain of Thought Reasonin…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2001.09977 — found via Mwmbl
[2001.09977] Towards a Human-like Open-Domain Chatbot
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2105.11447 — found via Mwmbl
[2105.11447] True Few-Shot Learning with Language Models
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2002.09018 — found via Mwmbl
[2002.09018] Scalable Second Order Optimization for Deep Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1705.11168 — found via Mwmbl
[1705.11168] Are distributional representations ready for the re…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2108.09135 — found via Mwmbl
[2108.09135] PatchCleanser: Certifiably Robust Defense against A…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1908.04734 — found via Mwmbl
[1908.04734] Reward Tampering Problems and Solutions in Reinforc…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1712.06567 — found via Mwmbl
[1712.06567] Deep Neuroevolution: Genetic Algorithms Are a Compe…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1901.10436 — found via Mwmbl
[1901.10436] Diversity in Faces
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1909.05858 — found via Mwmbl
[1909.05858] CTRL: A Conditional Transformer Language Model for …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1710.04615 — found via Mwmbl
[1710.04615] Deep Imitation Learning for Complex Manipulation Ta…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1603.04246 — found via Mwmbl
[1603.04246] The sphere packing problem in dimension 8
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2106.04263 — found via Mwmbl
[2106.04263] On the Connection between Local Attention and Dynam…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2006.12988 — found via Mwmbl
[2006.12988] A note on the Erdős distinct subset sums problem
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2110.13105 — found via Mwmbl
[2110.13105] Closure properties of $\varinjlim\mathcal C$
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2304.08485 — found via Mwmbl
[2304.08485] Visual Instruction Tuning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1712.05800 — found via Mwmbl
[1712.05800] The Hubble constant from SN Refsdal
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2301.09413 — found via Mwmbl
[2301.09413] Manticore: Hardware-Accelerated RTL Simulation with…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1702.07079 — found via Mwmbl
[1702.07079] Weyl versus Conformal Invariance in Quantum Field T…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1510.08042 — found via Mwmbl
[1510.08042] Weyl vs. Conformal
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1805.04829 — found via Mwmbl
[1805.04829] Spatial Uncertainty Sampling for End-to-End Control
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2210.16026 — found via Mwmbl
[2210.16026] The Skorokhod Topologies: What They Are and Why We …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2308.04835 — found via Mwmbl
[2308.04835] Search for magnetic monopoles and stable particles …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2310.08560 — found via Mwmbl
[2310.08560] MemGPT: Towards LLMs as Operating Systems
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2208.04097 — found via Mwmbl
[2208.04097] Detecting Extreme Ideologies in Shifting Landscapes…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2302.12351 — found via Mwmbl
[2302.12351] On the Hardness of Robustness Transfer: A Perspecti…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2302.10637 — found via Mwmbl
[2302.10637] A Survey of Trustworthy Federated Learning with Per…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1905.09228 — found via Mwmbl
[1905.09228] Jagged Islands of Bound Entanglement and Witness-Pa…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2107.03730 — found via Mwmbl
[2107.03730] Encoding Domain Information with Sparse Priors for …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2306.04007 — found via Mwmbl
[2306.04007] The asymptotics of $r(4,t)$
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2303.16199 — found via Mwmbl
[2303.16199] LLaMA-Adapter: Efficient Fine-tuning of Language Mo…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/0804.3888v1 — found via Mwmbl
[0804.3888v1] Witt vectors. Part 1
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2305.18811 — found via Mwmbl
[2305.18811] PyPOTS: A Python Toolbox for Data Mining on Partial…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2304.01433 — found via Mwmbl
[2304.01433] TPU v4: An Optically Reconfigurable Supercomputer f…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2105.07153 — found via Mwmbl
[2105.07153] Window-Level is a Strong Denoising Surrogate
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2303.06273 — found via Mwmbl
[2303.06273] Consistency Analysis of ChatGPT
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=352 — found via Mwmbl
Criticality and the brain « the physics arXiv blog
Our understanding of how various parts of brain function is advancing at breakneck speed and yet we are as far away as ever from an overarching “theory of…
-
http://arxivblog.com/?cat=14 — found via Mwmbl
At the seaside « the physics arXiv blog
Watch professional golfers putt and you’ll eventually notice three common features about their style, says Robert Grober, an expert on the physics of golf…
-
http://arxivblog.com/?p=142 — found via Mwmbl
Breaking the Netflix Prize dataset « the physics arXiv blog
Hell, this is good work. In October last year, Netflix released over 100 million movie ratings made by 500,000 subscribers to their online DVD rental serv…
-
http://arxivblog.com/?p=387 — found via Mwmbl
Solving the faint young Sun problem « the physics arXiv blog
Solving the faint young Sun problem We know by studying ancient rocks that liquid water existed on the surface of Earth at least 3.7 billion years ago. T…
-
http://arxiv.org/abs/math/0702389 — found via Mwmbl
[math/0702389] Multiplicative functions in arithmetic progressio…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math/0401246 — found via Mwmbl
[math/0401246] Lectures on tensor categories
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math/0605696 — found via Mwmbl
[math/0605696] Small gaps between prime numbers: The work of Gol…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=428 — found via Mwmbl
Can dark matter explain the flyby anomalies? « the physics arXiv…
The flyby anomalies, you may remember , are a set of fascinating data indicating that spacecraft flying past Earth undergo a strange, step-like change in …
-
http://arxivblog.com/?p=1266 — found via Mwmbl
The LHC’s dodgy dossier? « the physics arXiv blog
There’s no reason to worry about the Large Hadron Collider that is due to to be switched on later this year for the second time. The chances of it creatin…
-
http://arxivblog.com/?p=1186 — found via Mwmbl
The power laws behind terrorist attacks « the physics arXiv blog
The power laws behind terrorist attacks Plot the number of people killed in terrorists attacks around the world since 1968 against the frequency with whi…
-
http://arxiv.org/abs/1112.6209 — found via Mwmbl
[1112.6209] Building high-level features using large scale unsup…
Abstract: We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn …
-
https://arxiv.org/abs/math/0511001 — found via Mwmbl
[math/0511001] Teichmuller geodesics that do not have a limit in…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/math/0511602 — found via Mwmbl
[math/0511602] Vanishing of 3-Loop Jacobi Diagrams of Odd Degree
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2112.07558v1 — found via Mwmbl
[2112.07558v1] Multi-Modal Temporal Attention Models for Crop Ma…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxivblog.com/?cat=13 — found via Mwmbl
Sparks ‘n’ thunderbolts « the physics arXiv blog
There’s no reason to worry about the Large Hadron Collider that is due to to be switched on later this year for the second time. The chances of it creatin…
-
https://arxiv.org/abs/1406.2661 — found via Mwmbl
[1406.2661] Generative Adversarial Networks
Abstract: We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generativ…
-
https://arxiv.org/abs/1409.3215 — found via Mwmbl
[1409.3215] Sequence to Sequence Learning with Neural Networks
Abstract: Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well wh…
-
https://arxiv.org/abs/1312.6199 — found via Mwmbl
[1312.6199] Intriguing properties of neural networks
Abstract: Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition task…
-
https://arxiv.org/abs/1302.3925 — found via Mwmbl
[1302.3925] Cuboidal Dice and Gibbs Distributions
Title:Cuboidal Dice and Gibbs Distributions Abstract: What are the face-probabilities of a cuboidal die, i.e. a die with different side-lengths? This pap…
-
https://arxiv.org/abs/1009.2469 — found via Mwmbl
[1009.2469] Preprojective algebras and MV polytopes
Abstract: The purpose of this paper is to apply the theory of MV polytopes to the study of components of Lusztig's nilpotent varieties. Along the way, we …
-
https://arxiv.org/abs/1706.03762 — found via Mwmbl
[1706.03762] Attention Is All You Need
Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. T…
-
https://arxiv.org/abs/2005.14165 — found via Mwmbl
[2005.14165] Language Models are Few-Shot Learners
Abstract: Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tunin…
-
https://arxiv.org/abs/1906.01820 — found via Mwmbl
[1906.01820] Risks from Learned Optimization in Advanced Machine…
Abstract: We analyze the type of learned optimization that occurs when a learned model (such as a neural network) is itself an optimizer - a situation we …
-
https://arxiv.org/abs/1607.01032 — found via Mwmbl
[1607.01032] Echo Chambers: Emotional Contagion and Group Polari…
Abstract: Recent findings showed that users on Facebook tend to select information that adhere to their system of beliefs and to form polarized groups -- …
-
https://arxiv.org/abs/1512.03385 — found via Mwmbl
[1512.03385] Deep Residual Learning for Image Recognition
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substanti…
-
https://arxiv.org/abs/1712.05812 — found via Mwmbl
[1712.05812] Occam's razor is insufficient to infer the preferen…
Abstract: Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior. Since human planning systematically …
-
https://arxiv.org/abs/2209.11160 — found via Mwmbl
[2209.11160] TOI-5205 b: A Short-period Jovian Planet Transiting…
Abstract: We present the discovery of TOI-5205~b, a transiting Jovian planet orbiting a solar metallicity M4V star, which was discovered using Transiting…
-
https://arxiv.org/abs/1805.00899 — found via Mwmbl
[1805.00899] AI safety via debate
Abstract: To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to s…
-
https://arxiv.org/abs/1606.03137 — found via Mwmbl
[1606.03137] Cooperative Inverse Reinforcement Learning
Abstract: For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its …
-
https://arxiv.org/abs/2001.08361 — found via Mwmbl
[2001.08361] Scaling Laws for Neural Language Models
Abstract: We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, datase…
-
https://arxiv.org/abs/1712.01815 — found via Mwmbl
[1712.01815] Mastering Chess and Shogi by Self-Play with a Gener…
Abstract: The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination…
-
https://arxiv.org/abs/1609.08144 — found via Mwmbl
[1609.08144] Google's Neural Machine Translation System: Bridgin…
Abstract: Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weakne…
-
https://arxiv.org/abs/1912.01683 — found via Mwmbl
[1912.01683] Optimal Policies Tend to Seek Power
Abstract: Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of t…
-
https://arxiv.org/abs/1802.08908 — found via Mwmbl
[1802.08908] Scalable Private Learning with PATE
Abstract: The rapid adoption of machine learning has increased concerns about the privacy implications of machine learning models trained on sensitive dat…
-
https://arxiv.org/abs/2201.08239 — found via Mwmbl
[2201.08239] LaMDA: Language Models for Dialog Applications
Abstract: We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog,…
-
https://arxiv.org/abs/1710.05060 — found via Mwmbl
[1710.05060] Functional Decision Theory: A New Theory of Instrum…
Abstract: This paper describes and motivates a new decision theory known as functional decision theory (FDT), as distinct from causal decision theory and …
-
https://arxiv.org/abs/1711.00851 — found via Mwmbl
[1711.00851] Provable defenses against adversarial examples via …
Abstract: We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training…
-
https://arxiv.org/abs/1902.09725 — found via Mwmbl
[1902.09725] Conservative Agency via Attainable Utility Preserva…
Abstract: Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified rewa…
-
https://arxiv.org/abs/2301.02478 — found via Mwmbl
[2301.02478] Divergence vs. Decision P-values: A Distinction Wor…
Abstract: There are two distinct definitions of 'P-value' for evaluating a proposed hypothesis or model for the process generating an observed dataset. Th…
-
https://arxiv.org/abs/2305.10470 — found via Mwmbl
[2305.10470] Gravitational Machines
Abstract: A gravitational machine is defined as an arrangement of gravitating masses from which useful energy can be extracted. It is shown that such mach…
-
https://arxiv.org/abs/2202.02490 — found via Mwmbl
[2202.02490] Heaps, crystals, and preprojective algebra modules
Abstract:Fix a simply-laced semisimple Lie algebra. We study the crystal $ B(n\lambda)$, were $\lambda$ is a dominant minuscule weight and $n$ is a natur…
-
https://arxiv.org/abs/2308.00823 — found via Mwmbl
[2308.00823] Speed of Weak Mixing for the Chacon Map
Title:Speed of Weak Mixing for the Chacon Map Abstract:We first consider a non-primitive substitution subshift that is conjugate to the Chacon map. We th…
-
http://arxiv.org/abs/math.DG/0605667 — found via Mwmbl
[math/0605667] Notes on Perelman's papers
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.CT/0604542 — found via Mwmbl
[math/0604542] Finite Products are Biproducts in a Compact Close…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.AT/0212266 — found via Mwmbl
[math/0212266] Introduction to the language of stacks and gerbes
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.AP/0609692 — found via Mwmbl
[math/0609692] Global well-posedness and scattering for the mass…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.CO/0501170 — found via Mwmbl
[math/0501170] Tilings
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/hep-th/9501071 — found via Mwmbl
[hep-th/9501071] Les Houches Lectures on Black Holes
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/gr-qc/9405033 — found via Mwmbl
[gr-qc/9405033] Quasilocal Energy for a Kerr black hole
Abstract: The quasilocal energy associated with a constant stationary time slice of the Kerr spacetime is presented. The calculations are based on a rec…
-
https://arxiv.org/abs/hep-th/9701064 — found via Mwmbl
[hep-th/9701064] Conformal Invariance and Electrodynamics: Appli…
Abstract: The role of the conformal group in electrodynamics in four space-time dimensions is re-examined. As a pedagogic example we use the application o…
-
http://arxivblog.com/?p=1279&cpage=1 — found via Mwmbl
How superconducting sheets could reflect gravitational waves « t…
Gravitational waves are the elusive distortions in spacetime created by the universe’s most violent events–collisions between black holes, stars exploding…
New results
-
https://arxiv.org/ — found via Mwmbl
arXiv.org e-Print archive
arXiv is a free distribution service and an open-access archive for 2,183,548 scholarly articles in the fields of physics, mathematics, computer science, …
-
http://arxiv.org/abs/1411.4389 — found via Mwmbl
[1411.4389] Long-term Recurrent Convolutional Networks for Visua…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1205.2024 — found via Mwmbl
[1205.2024] Quantum teleportation and entanglement distribution …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1205.3909 — found via Mwmbl
[1205.3909] Quantum teleportation using active feed-forward betw…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/0811.2251 — found via Mwmbl
[0811.2251] The endpoint case of the Bennett-Carbery-Tao multili…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/0705.3773 — found via Mwmbl
[0705.3773] Circular law, Extreme Singular values and Potential …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1103.2759 — found via Mwmbl
[1103.2759] Quiver varieties and the character ring of general l…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=88 — found via Mwmbl
Cellphone records reveal new patterns of human activity « the ph…
Switch yer mobile phone on and it checks into the local network giving your location and the time you were there. The network also records the calls you m…
-
https://arxiv.org/abs/1312.6114 — found via Mwmbl
[1312.6114] Auto-Encoding Variational Bayes
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1307.2196 — found via Mwmbl
[1307.2196] Neural Dust: An Ultrasonic, Low Power Solution for C…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1609.03528 — found via Mwmbl
[1609.03528] The Microsoft 2016 Conversational Speech Recognitio…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1507.06947 — found via Mwmbl
[1507.06947] Fast and Accurate Recurrent Neural Network Acoustic…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/0809.2579 — found via Mwmbl
[0809.2579] Exercises in the birational geometry of algebraic va…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/1606.08954 — found via Mwmbl
[1606.08954] Greedy, Joint Syntactic-Semantic Parsing with Stack…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=596 — found via Mwmbl
Do nuclear decay rates depend on our distance from the sun? « th…
We think that the decay rates of elements are constant regardless of the ambient conditions (except in a few special cases where beta decay can be influen…
-
http://arxivblog.com/?p=370 — found via Mwmbl
Quantum zeno effect explains bird navigation « the physics arXi…
Quantum zeno effect explains bird navigation Just how birds use the earth’s magnetic field to navigate has puzzled researchers for decades. But in recent…
-
http://arxivblog.com/?p=664 — found via Mwmbl
The neglected puzzle of low energy nuclear reactions « the physi…
Cold fusion won’t go away and perhaps rightly so. Numerous groups have reported idiosyncratic behaviour of palladium hydrides sitting in heavy water when …
-
https://arxiv.org/abs/1810.04805 — found via Mwmbl
[1810.04805] BERT: Pre-training of Deep Bidirectional Transforme…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1707.06347 — found via Mwmbl
[1707.06347] Proximal Policy Optimization Algorithms
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1705.08807 — found via Mwmbl
[1705.08807] When Will AI Exceed Human Performance? Evidence fro…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1812.04948 — found via Mwmbl
[1812.04948] A Style-Based Generator Architecture for Generative…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2311.15421 — found via Mwmbl
[2311.15421] Wired Perspectives: Multi-View Wire Art Embraces Ge…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1712.00409 — found via Mwmbl
[1712.00409] Deep Learning Scaling is Predictable, Empirically
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1906.02825 — found via Mwmbl
[1906.02825] XRAI: Better Attributions Through Regions
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1810.08575 — found via Mwmbl
[1810.08575] Supervising strong learners by amplifying weak expe…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2002.11667 — found via Mwmbl
[2002.11667] An inverse theorem for Freiman multi-homomorphisms
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1905.12616 — found via Mwmbl
[1905.12616] Defending Against Neural Fake News
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1705.08417 — found via Mwmbl
[1705.08417] Reinforcement Learning with a Corrupted Reward Chan…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2107.03374 — found via Mwmbl
[2107.03374] Evaluating Large Language Models Trained on Code
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1906.08237 — found via Mwmbl
[1906.08237] XLNet: Generalized Autoregressive Pretraining for L…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1707.03497 — found via Mwmbl
[1707.03497] Value Prediction Network
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1911.09070 — found via Mwmbl
[1911.09070] EfficientDet: Scalable and Efficient Object Detecti…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1510.03055 — found via Mwmbl
[1510.03055] A Diversity-Promoting Objective Function for Neural…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1707.08945 — found via Mwmbl
[1707.08945] Robust Physical-World Attacks on Deep Learning Mode…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1802.01548 — found via Mwmbl
[1802.01548] Regularized Evolution for Image Classifier Architec…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1803.11175 — found via Mwmbl
[1803.11175] Universal Sentence Encoder
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1612.03801 — found via Mwmbl
[1612.03801] DeepMind Lab
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1710.09437 — found via Mwmbl
[1710.09437] Casper the Friendly Finality Gadget
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1611.01224 — found via Mwmbl
[1611.01224] Sample Efficient Actor-Critic with Experience Replay
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2103.03874 — found via Mwmbl
[2103.03874] Measuring Mathematical Problem Solving With the MAT…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1704.03477 — found via Mwmbl
[1704.03477] A Neural Representation of Sketch Drawings
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1804.08199 — found via Mwmbl
[1804.08199] Linguistically-Informed Self-Attention for Semantic…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2203.11171 — found via Mwmbl
[2203.11171] Self-Consistency Improves Chain of Thought Reasonin…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2001.09977 — found via Mwmbl
[2001.09977] Towards a Human-like Open-Domain Chatbot
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2105.11447 — found via Mwmbl
[2105.11447] True Few-Shot Learning with Language Models
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2002.09018 — found via Mwmbl
[2002.09018] Scalable Second Order Optimization for Deep Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1705.11168 — found via Mwmbl
[1705.11168] Are distributional representations ready for the re…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2108.09135 — found via Mwmbl
[2108.09135] PatchCleanser: Certifiably Robust Defense against A…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1908.04734 — found via Mwmbl
[1908.04734] Reward Tampering Problems and Solutions in Reinforc…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1712.06567 — found via Mwmbl
[1712.06567] Deep Neuroevolution: Genetic Algorithms Are a Compe…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1901.10436 — found via Mwmbl
[1901.10436] Diversity in Faces
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1909.05858 — found via Mwmbl
[1909.05858] CTRL: A Conditional Transformer Language Model for …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1710.04615 — found via Mwmbl
[1710.04615] Deep Imitation Learning for Complex Manipulation Ta…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1603.04246 — found via Mwmbl
[1603.04246] The sphere packing problem in dimension 8
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2106.04263 — found via Mwmbl
[2106.04263] On the Connection between Local Attention and Dynam…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2006.12988 — found via Mwmbl
[2006.12988] A note on the Erdős distinct subset sums problem
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2110.13105 — found via Mwmbl
[2110.13105] Closure properties of $\varinjlim\mathcal C$
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2304.08485 — found via Mwmbl
[2304.08485] Visual Instruction Tuning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1712.05800 — found via Mwmbl
[1712.05800] The Hubble constant from SN Refsdal
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2301.09413 — found via Mwmbl
[2301.09413] Manticore: Hardware-Accelerated RTL Simulation with…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1702.07079 — found via Mwmbl
[1702.07079] Weyl versus Conformal Invariance in Quantum Field T…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1510.08042 — found via Mwmbl
[1510.08042] Weyl vs. Conformal
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1805.04829 — found via Mwmbl
[1805.04829] Spatial Uncertainty Sampling for End-to-End Control
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2210.16026 — found via Mwmbl
[2210.16026] The Skorokhod Topologies: What They Are and Why We …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2308.04835 — found via Mwmbl
[2308.04835] Search for magnetic monopoles and stable particles …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2310.08560 — found via Mwmbl
[2310.08560] MemGPT: Towards LLMs as Operating Systems
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2208.04097 — found via Mwmbl
[2208.04097] Detecting Extreme Ideologies in Shifting Landscapes…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2302.12351 — found via Mwmbl
[2302.12351] On the Hardness of Robustness Transfer: A Perspecti…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2302.10637 — found via Mwmbl
[2302.10637] A Survey of Trustworthy Federated Learning with Per…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/1905.09228 — found via Mwmbl
[1905.09228] Jagged Islands of Bound Entanglement and Witness-Pa…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2107.03730 — found via Mwmbl
[2107.03730] Encoding Domain Information with Sparse Priors for …
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2306.04007 — found via Mwmbl
[2306.04007] The asymptotics of $r(4,t)$
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2303.16199 — found via Mwmbl
[2303.16199] LLaMA-Adapter: Efficient Fine-tuning of Language Mo…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/0804.3888v1 — found via Mwmbl
[0804.3888v1] Witt vectors. Part 1
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2305.18811 — found via Mwmbl
[2305.18811] PyPOTS: A Python Toolbox for Data Mining on Partial…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2304.01433 — found via Mwmbl
[2304.01433] TPU v4: An Optically Reconfigurable Supercomputer f…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2105.07153 — found via Mwmbl
[2105.07153] Window-Level is a Strong Denoising Surrogate
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2303.06273 — found via Mwmbl
[2303.06273] Consistency Analysis of ChatGPT
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=352 — found via Mwmbl
Criticality and the brain « the physics arXiv blog
Our understanding of how various parts of brain function is advancing at breakneck speed and yet we are as far away as ever from an overarching “theory of…
-
http://arxivblog.com/?cat=14 — found via Mwmbl
At the seaside « the physics arXiv blog
Watch professional golfers putt and you’ll eventually notice three common features about their style, says Robert Grober, an expert on the physics of golf…
-
http://arxivblog.com/?p=142 — found via Mwmbl
Breaking the Netflix Prize dataset « the physics arXiv blog
Hell, this is good work. In October last year, Netflix released over 100 million movie ratings made by 500,000 subscribers to their online DVD rental serv…
-
http://arxivblog.com/?p=387 — found via Mwmbl
Solving the faint young Sun problem « the physics arXiv blog
Solving the faint young Sun problem We know by studying ancient rocks that liquid water existed on the surface of Earth at least 3.7 billion years ago. T…
-
http://arxiv.org/abs/math/0702389 — found via Mwmbl
[math/0702389] Multiplicative functions in arithmetic progressio…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math/0401246 — found via Mwmbl
[math/0401246] Lectures on tensor categories
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math/0605696 — found via Mwmbl
[math/0605696] Small gaps between prime numbers: The work of Gol…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxivblog.com/?p=428 — found via Mwmbl
Can dark matter explain the flyby anomalies? « the physics arXiv…
The flyby anomalies, you may remember , are a set of fascinating data indicating that spacecraft flying past Earth undergo a strange, step-like change in …
-
http://arxivblog.com/?p=1266 — found via Mwmbl
The LHC’s dodgy dossier? « the physics arXiv blog
There’s no reason to worry about the Large Hadron Collider that is due to to be switched on later this year for the second time. The chances of it creatin…
-
http://arxivblog.com/?p=1186 — found via Mwmbl
The power laws behind terrorist attacks « the physics arXiv blog
The power laws behind terrorist attacks Plot the number of people killed in terrorists attacks around the world since 1968 against the frequency with whi…
-
http://arxiv.org/abs/1112.6209 — found via Mwmbl
[1112.6209] Building high-level features using large scale unsup…
Abstract: We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn …
-
https://arxiv.org/abs/math/0511001 — found via Mwmbl
[math/0511001] Teichmuller geodesics that do not have a limit in…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/math/0511602 — found via Mwmbl
[math/0511602] Vanishing of 3-Loop Jacobi Diagrams of Odd Degree
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/2112.07558v1 — found via Mwmbl
[2112.07558v1] Multi-Modal Temporal Attention Models for Crop Ma…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxivblog.com/?cat=13 — found via Mwmbl
Sparks ‘n’ thunderbolts « the physics arXiv blog
There’s no reason to worry about the Large Hadron Collider that is due to to be switched on later this year for the second time. The chances of it creatin…
-
https://arxiv.org/abs/1406.2661 — found via Mwmbl
[1406.2661] Generative Adversarial Networks
Abstract: We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generativ…
-
https://arxiv.org/abs/1409.3215 — found via Mwmbl
[1409.3215] Sequence to Sequence Learning with Neural Networks
Abstract: Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well wh…
-
https://arxiv.org/abs/1312.6199 — found via Mwmbl
[1312.6199] Intriguing properties of neural networks
Abstract: Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition task…
-
https://arxiv.org/abs/1302.3925 — found via Mwmbl
[1302.3925] Cuboidal Dice and Gibbs Distributions
Title:Cuboidal Dice and Gibbs Distributions Abstract: What are the face-probabilities of a cuboidal die, i.e. a die with different side-lengths? This pap…
-
https://arxiv.org/abs/1009.2469 — found via Mwmbl
[1009.2469] Preprojective algebras and MV polytopes
Abstract: The purpose of this paper is to apply the theory of MV polytopes to the study of components of Lusztig's nilpotent varieties. Along the way, we …
-
https://arxiv.org/abs/1706.03762 — found via Mwmbl
[1706.03762] Attention Is All You Need
Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. T…
-
https://arxiv.org/abs/2005.14165 — found via Mwmbl
[2005.14165] Language Models are Few-Shot Learners
Abstract: Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tunin…
-
https://arxiv.org/abs/1906.01820 — found via Mwmbl
[1906.01820] Risks from Learned Optimization in Advanced Machine…
Abstract: We analyze the type of learned optimization that occurs when a learned model (such as a neural network) is itself an optimizer - a situation we …
-
https://arxiv.org/abs/1607.01032 — found via Mwmbl
[1607.01032] Echo Chambers: Emotional Contagion and Group Polari…
Abstract: Recent findings showed that users on Facebook tend to select information that adhere to their system of beliefs and to form polarized groups -- …
-
https://arxiv.org/abs/1512.03385 — found via Mwmbl
[1512.03385] Deep Residual Learning for Image Recognition
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substanti…
-
https://arxiv.org/abs/1712.05812 — found via Mwmbl
[1712.05812] Occam's razor is insufficient to infer the preferen…
Abstract: Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior. Since human planning systematically …
-
https://arxiv.org/abs/2209.11160 — found via Mwmbl
[2209.11160] TOI-5205 b: A Short-period Jovian Planet Transiting…
Abstract: We present the discovery of TOI-5205~b, a transiting Jovian planet orbiting a solar metallicity M4V star, which was discovered using Transiting…
-
https://arxiv.org/abs/1805.00899 — found via Mwmbl
[1805.00899] AI safety via debate
Abstract: To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to s…
-
https://arxiv.org/abs/1606.03137 — found via Mwmbl
[1606.03137] Cooperative Inverse Reinforcement Learning
Abstract: For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its …
-
https://arxiv.org/abs/2001.08361 — found via Mwmbl
[2001.08361] Scaling Laws for Neural Language Models
Abstract: We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, datase…
-
https://arxiv.org/abs/1712.01815 — found via Mwmbl
[1712.01815] Mastering Chess and Shogi by Self-Play with a Gener…
Abstract: The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination…
-
https://arxiv.org/abs/1609.08144 — found via Mwmbl
[1609.08144] Google's Neural Machine Translation System: Bridgin…
Abstract: Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weakne…
-
https://arxiv.org/abs/1912.01683 — found via Mwmbl
[1912.01683] Optimal Policies Tend to Seek Power
Abstract: Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of t…
-
https://arxiv.org/abs/1802.08908 — found via Mwmbl
[1802.08908] Scalable Private Learning with PATE
Abstract: The rapid adoption of machine learning has increased concerns about the privacy implications of machine learning models trained on sensitive dat…
-
https://arxiv.org/abs/2201.08239 — found via Mwmbl
[2201.08239] LaMDA: Language Models for Dialog Applications
Abstract: We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog,…
-
https://arxiv.org/abs/1710.05060 — found via Mwmbl
[1710.05060] Functional Decision Theory: A New Theory of Instrum…
Abstract: This paper describes and motivates a new decision theory known as functional decision theory (FDT), as distinct from causal decision theory and …
-
https://arxiv.org/abs/1711.00851 — found via Mwmbl
[1711.00851] Provable defenses against adversarial examples via …
Abstract: We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training…
-
https://arxiv.org/abs/1902.09725 — found via Mwmbl
[1902.09725] Conservative Agency via Attainable Utility Preserva…
Abstract: Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified rewa…
-
https://arxiv.org/abs/2301.02478 — found via Mwmbl
[2301.02478] Divergence vs. Decision P-values: A Distinction Wor…
Abstract: There are two distinct definitions of 'P-value' for evaluating a proposed hypothesis or model for the process generating an observed dataset. Th…
-
https://arxiv.org/abs/2305.10470 — found via Mwmbl
[2305.10470] Gravitational Machines
Abstract: A gravitational machine is defined as an arrangement of gravitating masses from which useful energy can be extracted. It is shown that such mach…
-
https://arxiv.org/abs/2202.02490 — found via Mwmbl
[2202.02490] Heaps, crystals, and preprojective algebra modules
Abstract:Fix a simply-laced semisimple Lie algebra. We study the crystal $ B(n\lambda)$, were $\lambda$ is a dominant minuscule weight and $n$ is a natur…
-
https://arxiv.org/abs/2308.00823 — found via Mwmbl
[2308.00823] Speed of Weak Mixing for the Chacon Map
Title:Speed of Weak Mixing for the Chacon Map Abstract:We first consider a non-primitive substitution subshift that is conjugate to the Chacon map. We th…
-
http://arxiv.org/abs/math.DG/0605667 — found via Mwmbl
[math/0605667] Notes on Perelman's papers
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.CT/0604542 — found via Mwmbl
[math/0604542] Finite Products are Biproducts in a Compact Close…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.AT/0212266 — found via Mwmbl
[math/0212266] Introduction to the language of stacks and gerbes
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.AP/0609692 — found via Mwmbl
[math/0609692] Global well-posedness and scattering for the mass…
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
http://arxiv.org/abs/math.CO/0501170 — found via Mwmbl
[math/0501170] Tilings
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/hep-th/9501071 — found via Mwmbl
[hep-th/9501071] Les Houches Lectures on Black Holes
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations tha…
-
https://arxiv.org/abs/gr-qc/9405033 — found via Mwmbl
[gr-qc/9405033] Quasilocal Energy for a Kerr black hole
Abstract: The quasilocal energy associated with a constant stationary time slice of the Kerr spacetime is presented. The calculations are based on a rec…
-
https://arxiv.org/abs/hep-th/9701064 — found via Mwmbl
[hep-th/9701064] Conformal Invariance and Electrodynamics: Appli…
Abstract: The role of the conformal group in electrodynamics in four space-time dimensions is re-examined. As a pedagogic example we use the application o…
-
http://arxivblog.com/?p=1279&cpage=1 — found via Mwmbl
How superconducting sheets could reflect gravitational waves « t…
Gravitational waves are the elusive distortions in spacetime created by the universe’s most violent events–collisions between black holes, stars exploding…