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 200
Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning
Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a model from scratch.Finite-Time Guarantees for Constrained Reinforcement Learning under Partial Observability
We study reinforcement learning in constrained partially observable Markov decision processes (CPOMDPs), where an agent maximizes reward subject to a cost constraint using only incomplete…When Is Muon Optimal? Radial Fragility and Minimax Geometry
Muon replaces a matrix gradient by an approximate polar factor and has shown strong empirical performance in neural-network training.Rethinking Classifier-Free Guidance for TI2I Flow Matching
We study Text-and-Image-to-Image (TI2I) flow matching methods for controllable image editing.Uncertainty Quantification in Pairwise Difference Learning for Classification
Instead of learning a mapping from instances to outcomes in the standard way, the key idea of pairwise difference learning (PDL) is to learn a function that takes two instances as input and predicts…When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark
Muon's gains in data efficiency motivate evaluating its performance under explicit data, time, and tuning budgets.Reducing the Cost of Qudit State Preparation by Learning a Sparse Structure for SNAP Gates
Preparing quantum states in bosonic qudits with SNAP--Displacement sequences requires both optimizing the gate parameters and deciding which Fock levels should be controlled by each SNAP gate.DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic.A Quantum Machine Learning Approach to Content-Based Media Recommendation
We use quantum machine learning techniques to develop a content-based media recommender system and evaluate its performance on TV programmes using textual descriptions from one week of BBC iPlayer…Sharp and Stable Label-Free Calibration Certificates from Logical Coherence
Query-conditioned probabilistic predictors answer logically related questions one at a time, and labels to check their calibration are often missing.From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios
Recent multimodal large language models have advanced video understanding, but existing benchmarks mainly evaluate whether models can interpret observed visual content.Learning to Search for Executable Patternmaking from Certified Programs
Recent models generate sewing patterns from images or text, and program-based representations make these patterns executable.ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing
Mathematical agents are commonly evaluated by answer accuracy or proof acceptance.Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds
Transfer learning in stochastic multi-armed bandits is typically studied assuming that prior data forms a fixed offline dataset or is generated by a known source.LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models
Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers.Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories.Market Incentives for AI Safety Investment
Despite their practical significance, modern AI systems pose significant societal risks, including toxicity, malicious use, and misinformation.Local Temporal Contrasts on Human Motion Data Induce a Latent Geometry
Time series such as recordings of human motion data often encode structure across multiple temporal scales, and when a latent state determining this sequence evolves, this structure needs to survive…ContextLift: Breaking the Spurious Correlation Behind Conditional Emergent Misalignment
Finetuning a language model on narrowly misaligned data can make it broadly misaligned.ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
Reinforcement learning (RL) has been a critical paradigm for improving large language model (LLM) reasoning and agentic capabilities, but its efficiency remains a major bottleneck.