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 119
Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data
Supervised contrastive learning and its balanced variants have demonstrated their effectiveness for representation learning under long-tailed distributions.NUViT: Vision Transformers for Fourier Space Data
Vision Transformers (ViTs) have demonstrated strong performance in many computer vision tasks but do not naturally extend beyond the natural image domain.Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery…A Dynamic Inventory Rationing Model for Last-Mile Delivery of Medication in Liberia's Community Health Program
We study the dynamic allocation of scarce medications in Liberia's community health program.How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models
Large language models (LLMs) often exhibit sycophancy, altering their answers to align with user suggestions even on objective factual and reasoning tasks.Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content, motivating machine unlearning (MU) to selectively remove target concepts…Controlled Evaluation of EEG Foundation Models: Random Initialisation, Band-Power and Validation-Selected Probes
EEG foundation models report downstream gains, yet their protocols seldom include three controls.DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting
Non-stationarity induces test-time distribution shifts in time series forecasting (TSF), resulting in forecast residuals between predictions and the corresponding ground truth.RADIANT: Object-Centric Feed-Forward Global Illumination
Feed-forward neural renderers synthesize global illumination across novel 3D scenes without per-scene optimization or runtime ray tracing.PRISM: Promoting Sampling Diversity of Large Language Models with Implicit Stochastic Modulation
Large language models (LLMs) exhibit mode collapse, where their output distribution concentrates on familiar semantic modes.ReMedI: Inference-Time Refinement and Self-Distillation for Controllable Molecular Optimization
In drug development, lead optimization must improve competing properties, such as increasing permeability and reducing toxicity, while limiting scaffold changes that could compromise the lead's…Putting Transformer Theories to the Test
Several formal theories have been developed to characterize the capabilities and limitations of the transformer architecture, each employing different abstractions that capture different features of…REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories
Chain-of-thought (CoT) generation offers an opportunity to intervene before a reasoning model completes its answer.Tampered ML: Evaluating LLM Judgment of Machine Learning Research
One approach to accelerating progress on AI alignment is to automate parts of alignment research itself.Semantically Rich, Metrically Affect-Blind: A Geometric Blind Spot in Modern Text Embedders
We report a systematic dissociation in modern text embedders: sentiment is almost perfectly decodable from their embeddings, yet almost entirely absent from their metric.Conditional Flow Models for Offline Maximum Entropy Reinforcement Learning
Offline maximum entropy reinforcement learning seeks to estimate the optimal soft action-value function \(Q^*\) from a fixed dataset without further interaction with the environment.MPQ: A Message-Passing View of Post-Training Quantization
Post-training quantization (PTQ) is a key technique for efficiently deploying large language models, as it compresses weights into low-bit representations without retraining.SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding
Proactive streaming video understanding requires assistants to track unfolding events and respond when a user's requested condition is met.Beyond Data Schedule: Fast LLM Pretraining on Data Mixtures by Loss-Reweighting
Large language models often acquire specialized capabilities through successive pretraining stages, but these gains can come at the cost of forgetting earlier knowledge.Rethinking LoRA Initialization for Robust Asymmetric Learning Rates
Low-Rank Adaptation (LoRA) is often highly sensitive to learning-rate (LR) choices.