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 19
Task-Calibrated Random Features via Influence-Based Error Cancellation
Random features approximate kernel integrals by Monte Carlo, yet only selected frequency-sampling errors affect a downstream task.Canonical Correlation Neural Networks
Relational inductive biases such as grids or graphs allow neural networks with fewer trainable parameters and improved generalization, but require a known structure beforehand.Fractional physics-informed neural networks to model social media virality
Existing models of social media virality either prescribe the functional form of engagement growth or assume a fixed mechanism by which past activity influences future engagement.Compositional Unalignment: Auditing Safety in Large Vision-Language Models
Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning.TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization
Post-training quantization (PTQ) reduces large language model (LLM) deployment costs, but preserving quality requires accounting for uneven weight sensitivity.Loopback Transformer: Towards a Unified View of Residual Looped Transformers
Looped Transformers reduce parameter count by repeatedly applying shared blocks, but parameter sharing alone does not determine how the results of repeated computation are reused.Recursive Sparse Attention: Million-Token Length Extrapolation at Logarithmic Cost
At context lengths of about 1M tokens, dense attention is costly in prefill and decoding, and training typically relies on long documents, which become scarcer as the target length increases.Neural Compression over Equivalence Classes: Exact Gauges and Functional Rate-Distortion
Neural networks admit many parameterizations of the same or nearly the same function, but deployment typically stores whichever parameter vector training happens to produce.Archetypal contexts in the neurons of language models: an architecture for intelligence?
We validate our previous hypothesis that a language model holds relational patterns apart from the subject domains that instantiate them (Nordfors, 2026).$D^2$-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation
On-policy distillation (OPD) trains a student model to match a teacher's next-token distributions on student-generated prefixes.MAC-v2: Long-horizon model-based value expansion from pixels
We study whether \emph{long-horizon model-based value expansion} can serve as an effective framework in pixel-based offline reinforcement learning (RL).KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization
In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships.Goal Revelation as a Bridge Between Information-Theoretic Empowerment and Capability-Based Human Power
Power matters for AI safety.ScaleTraj: Scale-Decomposed Human Trajectory Generation
Individual-level trajectories are essential for applications that rely on user-level mobility behavior.When Strong Reasoners Join the Pool: Small Union Premiums and Costly Runaway Generations in LLM Routing
Routing benchmarks often judge a router against a hindsight oracle that counts a query as solved whenever any model's recorded answer is correct, but under stochastic decoding that oracle mixes two…ModelBlaster: Closing the Performance Gap through Learning-Augmented Agents Across Models, Kernels and Hardware Backends
Optimizing accelerator code across hardware architectures is difficult.Structure, Dimensionality, and Distribution Shape - What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which
What makes a pretraining corpus transferable?Separating Common and Unique Directions for Model Merging
Model merging combines multiple fine-tuned models without additional training, and arithmetic methods have emerged as a simple yet effective way to merge models without data.Co-Occurrence Priors Override Visual Spatial Evidence: Understanding False Alarms in Vision-Language Models for Construction Struck-By Hazard Detection
Vision-language models (VLMs) increasingly support construction hazard monitoring, yet their frequent false alarms remain poorly understood.Decomposing Rank Reversals under Temporal Nonstationarity: Alignment, Aggressiveness, and Instability
Under temporal nonstationarity, model performance rankings reverse across training horizons due to heterogeneous sensitivities to memory.