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 17
Visual Token Routing: Learning to keep tokens that matter
Computer-use agents (CUAs) have recently achieved superhuman performance on several long-horizon benchmarks.Balancing hierarchical representation and quantization: A performance trade-off in text embeddings
Hierarchical text embedding models offer variable-length representations, while quantization reduces numerical precision; both aim to improve computational efficiency.CounterFactual Retrieval for Evidence-Aware Individual Animal Identification
Automated identification of individual animals is moving from small curated studies toward shared benchmarks and reusable foundation models.Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes
The best classical optimizer for a continuous black-box problem depends on its budget and landscape.Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement
The introduction of generalist robot policies has enabled a single, large model to learn to perform a variety of tasks from a vast pre-training corpus.Perceptive Humanoid Motion from Simulation
Humanoid robots have the potential to automate a wide range of physical tasks.FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors
Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables.A Framework for Context Enrichment and Selective Robustness in LLM Social Agents
Researchers use large language models as agents in social simulations, where agents are prompted with observations and background information intended to shape their actions.Uncertainty calibration in Bayesian M/EEG source imaging
M/EEG source imaging requires accurate localization and reliable uncertainty estimates, yet posterior credible regions are rarely assessed for empirical calibration.Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER
Forecasting foundation models are increasingly used as frozen feature extractors for time series classification, but it remains unclear whether their pretrained representations offer an advantage…ToroFit: Fitting Wedge Sums of Tori to High-Dimensional Data
Data arising in scientific applications often exhibits complex nonlinear structure.Robust Stream Classification using Time Neutralising Decision Trees
Data Streams are characterised as a potentially infinite source of data subject to non-stationarity.LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time
Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch size and throughput.Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs
This paper develops a stochastic dynamical-systems perspective on three classes of generative AI models.Finite-Time Convergence and Regret Guarantees for Neural Reinforcement Learning in POMDPs
Reinforcement learning (RL) in Partially Observable Markov Decision Processes (POMDPs) is computationally challenging due to the curse of long-range dependence on history.Shaping & Monitoring Models through their Internal Representations
We propose Mechanistic Shaping, a unified framework for shaping models through their internal representations.Optimistic Hedge in General-Sum Games: Fundamental Limits and Regret Bounds via Temporal Approximation
Optimistic Hedge, a multiplicative weight update with one step of extrapolation, is one of the most natural regret-minimizing dynamics for games, and characterizing its regret has been a…Synthesizing symbolic models of human and machine reasoning at scale
Symbolic models offer a powerful account of cognition, but their scope has historically been limited by the need for hand-engineering and computational tractability.Server-Side Sparse Assignment for Federated Mixture-of-Experts
Large language models (LLMs) are increasingly recognized for their remarkable capabilities; federated learning (FL) offers a promising framework for collaboratively fine-tuning LLMs on edge devices…A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights
A challenge to Weight Space Learning as it expands from task specific and vision models to Large Language Models (LLMs) is the absence of a well curated and analyzed LLM population.