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 199
Does Compression Imply Generalization? A Minimum Description Length Perspective
A central question in modern learning theory is what notion of compression, if any, explains why over-parameterized neural networks generalize.RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases
Relational databases (RDBs) remain the primary infrastructure for storing and managing structured data across enterprise and scientific domains.Calibration Language Shapes Block-Influence Pruning in Multilingual Language Models
Block Influence (BI) ranks Transformer blocks for depth pruning from their input-output cosine change, but the ranking depends on the calibration distribution.Self-Guided LLM Reasoning for Error Diagnosis in Vehicle Routing Problems
Vehicle Routing Problems (VRPs) are fundamental to many real-world applications.Fault Detection and Bit-Error Rate Diagnostics in Optical Wireless Links Using Edge-AI
Optical Wireless Communication (OWC) systems provide high-bandwidth, spatially secure, and RF-interference-free digital transmission.Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal Learning
Distribution shifts pose a fundamental challenge to robust multimodal learning.Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense
To improve task performance while encouraging desirable response properties, LLM post-training often combines a primary reward (e.g., correctness) with auxiliary rewards (e.g., brevity or efficiency).Learning to Forecast on Multiple Spatiotemporal Hierarchies
Hierarchical forecasting exploits aggregation structures that expose multiple views of the same underlying spatiotemporal forecasting problem, while ensuring coherence among forecasts.What Does History Add? Calendar Controls and Information-Timing Audits for University Trajectory Forecasting
We audit the predictive value of historical summaries in a rule-based university trajectory simulator.ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space
Diffusion models achieve high-quality image generation but remain computationally expensive due to iterative denoising across many timesteps.Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk Execution
Vision-language-action (VLA) policies generate action sequences that reduce repeated inference, but deciding how much of each sequence to execute is critical to task success.HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative Decoding
Device-cloud speculative decoding reduces server computation, but growing a deep draft tree with a small language model (SLM) requires repeated passes on a mobile neural processing unit (NPU).Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL
Language models are increasingly trained against several verifiable rewards at once, such as the correctness and the format of a tool call, or the individual constraints of a complex instruction.V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms
In reinforcement learning, advantage-based value-learning methods, unlike standard Q-learning, share information across actions by decomposing the action-value function into a state-dependent value…Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routine enough for a…DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription
Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure.Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias
Kolmogorov-Arnold networks (KANs) have a dimension-independent approximation exponent when the target admits a sufficiently smooth representation by univariate edge functions.Phase Kernel Lifts Capacity of Dense Associative Memory
Dense associative memory underlies modern attention mechanisms; however, Modern Hopfield Networks (MHNs) with linear kernels yield overlapping attractor basins and spurious states under high memory…When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill
Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly back the per-engine cache with a remote tier…Activation-Adjacent Layer Normalization: Effects on Approximation Power
Layer normalization (LN) and root mean square normalization (RMSNorm) depend on their inputs and remain nonlinear at inference.