AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 205
Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics
The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream.Mosaic: Multi-Session Agentic Reinforcement Learning
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context.REKI: Registering Knowledge in VLAs
We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model size: on LIBERO-Plus, RoboTwin…LCT: Losslessly Compressed Tensors with GPU friendly execution for Training
Lossless tensor compression could reduce memory usage during training, but training requires tensors to be repeatedly re-encoded.Whole-Body Dexterity
Current humanoid dexterous manipulation remains largely confined to end-effectors and simple grasps, falling short of humans' ability to engage the entire body by bracing and sliding bulky objects…Attention over noisy examples: generalization and memorization in the exponential Hopfield network
In Hebbian learning from examples, a Hopfield network retrieves archetypes seen only through noisy examples.Beyond Downstream QA: Rethinking How We Evaluate Agent Memory
Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy for memory quality.Generalization Guarantees of Randomized Block Coordinate Descent for Nonconvex Learning
Randomized block coordinate descent (RBCD) is a popular optimization algorithm for many large-scale machine learning problems.FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting
Accurate motion prediction is critical for safe autonomous driving, yet even strong forecasters leave residual errors in their multimodal proposals.How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping Structure
Physical understanding is crucial for decision making, yet vision models struggle to infer properties such as damping that govern how materials behave.Architecting for Hardware Diversity: Meta's End-to-End Co-Design for High-Performance AI Training on AMD GPUs
Meta deploys a heterogeneous fleet comprising NVIDIA GPUs, AMD GPUs, and proprietary MTIA accelerators to reduce costs and mitigate vendor lock-in.OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
Real desktop automation is neither purely visual nor purely programmatic.Training-Free On-Policy Distillation
On-policy distillation consolidates specialist models into one student at the price of rollouts, teacher passes and gradient steps for every teacher.Query-Efficient Rejection Sampling for Parallel Masked Diffusion
Masked diffusion models (MDMs) accelerate generation by unmasking multiple tokens in parallel, but sampling these tokens independently ignores their correlations and biases the output.SurvICL: a Foundation Model for in-context Survival Analysis
Tabular foundation models (TFMs) now outperform gradient-boosted trees in classification and regression.Shortcut Sensitivity in Agent-Safety Evaluations
AI agents take actions through tools.Language Is a Security Surface for Agent Guards
Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far.Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits
We study how to evaluate $K$ target policies simultaneously in stochastic contextual bandits with linear reward structure.BitSparse: Compact Activation Storage for ReLU Feed-Forward Networks
Reducing memory use in large language model (LLM) training is an ongoing challenge.Topology-Inspired Fine-Tuning for Wind-Field Super-Resolution
Scientific super-resolution (SR) models are typically optimized with pointwise reconstruction losses, yet scientific interpretation often hinges on extrema, connected regions, and multiscale scalar…