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 234
Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast
Accurate uncertainty quantification is critical for many time series forecasting applications, and recent studies have increasingly adopted generative models to capture predictive uncertainty.Minimax rates for pointwise CATE estimation: the role of design smoothness
We study the role of design smoothness in the minimax estimation of conditional average treatment effects at a fixed covariate point.MajorTOM:Elliot Pretrain, A Multi-Sensor, Multi-Temporal Pretraining Dataset for Earth Observation
Pretraining generalist Earth observation foundation models requires data that combine several sensors, varied temporal sampling and, increasingly, text, yet open datasets rarely provide all three in…Geometric Calibration of Supervised Fine-Tuning
Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directions.Grid or Nodes? Probing Object Memory in World Models Under Partial Observability
A robot's world model must remember objects that leave the camera's view.To Align or Not To Align: Check Your COMPASS Before You Train
Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints.MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization
The Key-Value (KV) cache constitutes a dominant source of memory consumption during large language model (LLM) inference, particularly in long-context and complex reasoning scenarios.Tiny Recursive Message Passing
Message passing neural networks have shown remarkable performance in algorithmic and constraint reasoning, due to their ability to encode the structure of the task directly in the architecture.Does Pretraining Teach Chemical Language Models Chemistry?
Chemical language models (CLMs) are pretrained on large corpora of molecules with the aim of learning representations that transfer to diverse downstream tasks.AMemOps: Evaluating Memory Updates in Long Audio Streams
Audio memory must recognise recurring sources across acoustic changes while keeping their attributes up to date.Kwai Summary Attention V2 Technical Report
token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave these layers with full attention to retain…Texture Interpolation as Texton Matching
Texture interpolation asks what should lie between two textures.Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses.BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
Generative models are often required to serve many downstream conditional tasks.Model-Based Online Decision Making via Generative Trajectory Planning
Online decision-making faces a tension between efficient inference and long-horizon reasoning.ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fundamental uniform…Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents
Personal-agent memory has largely focused on learning what users know, prefer, and want.Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning
Image-token compression must reduce computation without hurting the semantics.GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models
Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations.A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training
Kronecker-preconditioned optimizers recompute a cached curvature eigendecomposition only periodically, and implementations and adaptive methods control this through the refresh frequency.