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 20
ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking
Existing attacks treat evasion as a removal problem: they erase the watermark, relying on detector access or on speech data that is hard to collect, such as paired clean-watermarked or clean target…LoopKV: Loop-Aware KV Cache Compression for Serving Looped Transformers
Looped transformers apply a shared block several times per token to improve accuracy without adding parameters.Where Do Distilled Students Store Thinking?
Small students degrade on large reasoning models' (LRMs') long solutions, so recent work shortens them by interpolating an LRM with a short-answer model at ratio $λ$.RGDM: Robust Graph Diffusion Model
Diffusion models represent a powerful class of generative models known for their solid theoretical foundations and remarkable performance across diverse tasks and domains.Nonparametric GARCH: An Iterated Neural Estimator
We study nonparametric estimation and forecasting for GARCH-type processes and propose an iterated neural estimator that alternates between estimating the recursion map and updating the unobserved…On the Feature Evolution of Temporal Difference Learning
Temporal-difference (TD) learning trains neural representations using bootstrapped targets generated by evolving value estimates, yet how predictive features emerge and propagate under incomplete…What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting
Long-horizon video generation is increasingly moving toward autoregressive rollout, where each newly generated segment becomes part of the evidence used for future prediction.Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs
Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety.Descending Everest, Part II: Oracle Complexity of Minimizing a Sum of Convex $(L_0,L_1)$-Smooth Functions
We study the minimization of the average of $n$ convex $(L_0,L_1)$-smooth functions: the Hessian norm of each function is bounded by an affine function of its gradient norm.What Does 4-Bit Microscaling Cost a Wearable Activity Recognizer?
Wearable sports sensors can recognize actions on the device itself, where lower-precision numbers reduce model storage and memory traffic.Where Did the Update Go? Certifying Declared Change Envelopes for Model Updates
Deployed language models are updated continually, and regulators increasingly accept changes that were declared in advance.An Information Budget for Label-Noise Memorization, and What Statistical Complexity Tracks: A Study with Multilayer Perceptrons
How much label noise has a network memorized, and when?Impact of Input Resolution in Mammographic Mass Detection: A Controlled Multi-Architecture Study
Deep-learning-based mass detectors usually downsample mammograms, trading fine image detail for lower computational cost.Point interpolation and distributional universality in flow-based generative models
Motivated by the expressive power of neural ordinary differential equations in flow-based generative modeling, we study the approximation of probability measures by pushforwards generated by…Two-Layer Random ReLU Networks Can Separate Disjoint Classes
Set separation by continuous linear functionals is fundamental in functional analysis and convex optimization and underlies binary classification in machine learning.Tokenizer Myths and Where To Find Them
Tokenization is a fundamental component of modern language models: before a model sees data, its tokenizer has already determined how the data appears.LENS: Reliability-Aware Stock Prediction via LLM-Extracted Priors and News-Driven Semantic Graphs
Predicting stock returns requires modeling persistent company relations and time-varying market signals.GC-MoE: Overlapping Expert-Parallel Token Dispatch with FP8/FP4 Grouped GEMM via CUDA Green Contexts
Under expert parallelism, mixture-of-experts (MoE) layers pay all-to-all token dispatch, grouped GEMMs, and a combine step in every layer.LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation
Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large pretrained models.OmniST: Topology-Invariant Spatiotemporal Forecasting with Guaranteed-Coverage Uncertainty at Unseen Sensor Locations
Standard spatiotemporal graph convolutional networks need a fixed-size adjacency matrix, coupling model weights to a specific sensor count N; they cannot produce any output at a sensor absent from…