arXiv cs.LG

Machine Learning daily digest.

52 past editions, oldest first by date. Atom feed → · all categories

01 — Past editions

most recent first

2026-07-19 Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier 53 papers · No. 58
2026-07-18 Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier 53 papers · No. 57
2026-07-17 Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier 53 papers · No. 56
2026-07-16 Leveraging unlabelled data for generalizable neural population decoding 66 papers · No. 55
2026-07-15 The Seriality Gap in Video Diffusion Models 53 papers · No. 54
2026-07-14 Requential Coding: Pushing the Limits of Model Compression with... 59 papers · No. 53
2026-07-13 Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for... 69 papers · No. 52
2026-07-12 SLORR: Simple and Efficient In-Training Low-Rank Regularization 60 papers · No. 51
2026-07-11 SLORR: Simple and Efficient In-Training Low-Rank Regularization 60 papers · No. 50
2026-07-10 SLORR: Simple and Efficient In-Training Low-Rank Regularization 60 papers · No. 49
2026-07-09 The Key to Going Linear: Analysis-Driven Transformer Linearization 81 papers · No. 48
2026-07-08 Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and... 40 papers · No. 47
2026-07-07 Weak-to-Strong Generalization via Direct On-Policy Distillation 73 papers · No. 46
2026-07-06 Program-as-Weights: A Programming Paradigm for Fuzzy Functions 55 papers · No. 45
2026-07-05 Program-as-Weights: A Programming Paradigm for Fuzzy Functions 55 papers · No. 44
2026-07-04 Program-as-Weights: A Programming Paradigm for Fuzzy Functions 55 papers · No. 43
2026-07-03 Program-as-Weights: A Programming Paradigm for Fuzzy Functions 55 papers · No. 42
2026-07-02 Is One Layer Enough? Training A Single Transformer Layer Can Match... 68 papers · No. 41
2026-07-01 QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents 55 papers · No. 40
2026-06-30 One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous... 62 papers · No. 39
2026-06-29 VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward... 73 papers · No. 38
2026-06-28 Reinforcement Learning without Ground-Truth Solutions can Improve LLMs 58 papers · No. 37
2026-06-27 Reinforcement Learning without Ground-Truth Solutions can Improve LLMs 58 papers · No. 36
2026-06-26 Reinforcement Learning without Ground-Truth Solutions can Improve LLMs 58 papers · No. 35
2026-06-25 RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments 63 papers · No. 34
2026-06-24 Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's... 33 papers · No. 33
2026-06-23 Open Problem: Is AdamW Effective Under Heavy-Tailed Noise? 76 papers · No. 32
2026-06-22 How Transparent is DiffusionGemma? 66 papers · No. 31
2026-06-21 How Transparent is DiffusionGemma? 66 papers · No. 30
2026-06-20 How Transparent is DiffusionGemma? 66 papers · No. 29
2026-06-19 How Transparent is DiffusionGemma? 66 papers · No. 28
2026-06-18 UBP2: Uncertainty-Balanced Preference Planning for Efficient... 71 papers · No. 27
2026-06-17 Sign-Rank, Index, and List Replicability: Connections and Separations 59 papers · No. 26
2026-06-16 Exact Posterior Score Estimation for Solving Linear Inverse Problems 65 papers · No. 25
2026-06-15 Persona-Pruner: Sculpting Lightweight Models for Role-Playing 72 papers · No. 24
2026-06-14 Understanding Truncated Positional Encodings for Graph Neural Networks 62 papers · No. 23
2026-06-13 Understanding Truncated Positional Encodings for Graph Neural Networks 62 papers · No. 22
2026-06-12 Understanding Truncated Positional Encodings for Graph Neural Networks 62 papers · No. 21
2026-06-11 Redesign Mixture-of-Experts Routers with Manifold Power Iteration 61 papers · No. 20
2026-06-10 When to Align, When to Predict: A Phase Diagram for Multimodal Learning 74 papers · No. 19
2026-06-09 An Agency-Transferring Model-Free Policy Enhancement Technique 64 papers · No. 18
2026-06-08 Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning 73 papers · No. 17
2026-06-07 TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning 59 papers · No. 16
2026-06-06 TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning 59 papers · No. 15
2026-06-05 TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning 59 papers · No. 14
2026-06-02 IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning 59 papers · No. 13
2026-05-30 Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching 64 papers · No. 12
2026-05-28 PEFT-Arena: Understanding Parameter-Efficient Finetuning from a... 65 papers · No. 11
2026-05-27 MobileMoE: Scaling On-Device Mixture of Experts 66 papers · No. 10
2026-05-25 LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws 52 papers · No. 9
2026-05-23 Vector Policy Optimization: Training for Diversity Improves Test-Time Search 39 papers · No. 8
2026-05-22 Vector Policy Optimization: Training for Diversity Improves Test-Time Search 39 papers · No. 7

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.