AI News

Where Does Timbre Hide? Localizing Speaker Information in Speech Signals (arxiv.org)

AI-Based End-to-End Automotive Design and Software Development for SDVs (arxiv.org)

Why is AI-generated language so hard to understand? (arxiv.org)

XALIGN: A Human-centric Visual Analytics Approach to Understanding AI Explanations (arxiv.org)

Federated Differentially Private Optimization via Low-Rank Preconditioning (arxiv.org)

On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders (arxiv.org)

Consistency Is Not Validity: Self-Rewarded Moral Argumentation Makes Language Models Decisive but Pliable (arxiv.org)

Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs (arxiv.org)

A Transformer-based Approach for Real-time Multi-agent Path Planning with Varying Initial/Final Conditions (arxiv.org)

How Representational Priors Shape Generalization in World Action Models (arxiv.org)

TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence (arxiv.org)

Correlated Failures of AI Approval Monitors (arxiv.org)

Resuming Vision-Language Inference across Onboard Interruptions (arxiv.org)

Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning (arxiv.org)

A Quadratic Lens on Muon's Polar Update: Benefits, Pitfalls, and the Role of Newton-Schulz (arxiv.org)

SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents (arxiv.org)

Generalizing Metropolis-Hastings for DAG Sampling (arxiv.org)

GAV: A scientific experimentation environment for PDE agents (arxiv.org)

Events, Not Pixels: Where World Models Get the Return Wrong (arxiv.org)

PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents (arxiv.org)

RubricOpt: Self-Revision of Semantic Rubrics for Preference Optimization (arxiv.org)

An Exact 93-Move Solution to a Nonlocal Crystal-Exchange Puzzle (arxiv.org)

Zero-Cost Detection of Fabricated Citations: A Staged Heuristic Approach for Computing Dissertation Assessment (arxiv.org)

Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications (arxiv.org)

CTRL-FM: Inference-Time Structural Control for Flow-Based Virtual Sensing under Long-Horizon Node Outages (arxiv.org)

Probing and Steering for Safety-Relevant Behaviours in Large Language Models (arxiv.org)

Bayesian Fixed-Confidence Best-Arm Identification with Abstention (arxiv.org)

FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning (arxiv.org)

The CIDOC CRM Periodic Table: Documentation You Can Test to Support the Adoption of Scientific Research Ontologies for the Humanities (arxiv.org)

FutureLens: Longitudinal Topic Patterns in Scholarly Text and Future-Work References (arxiv.org)

CompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet Needs (arxiv.org)

How to Use Parallel Data for Multilingual Pretraining (arxiv.org)

Agent AI Zarz\k{a}dzaj\k{a}cy Sieci\k{a} Open RAN Zorientowana na U\.zytkownika (arxiv.org)

Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks (arxiv.org)

A Computationally Efficient and Rate-Optimal Algorithm for Adversarial Linear MDPs with (Aggregate) Bandit Feedback (arxiv.org)

Is spectral predictability enough? Testing {\Omega}-matching for synthetic pretraining under distribution shift (arxiv.org)

Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers (arxiv.org)

Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries (arxiv.org)

Reverse-KL Policy Distillation: Statistical Guarantees and Limits (arxiv.org)

Bifurcations from Weight Space: JEPAWG on Parametric Dynamical Systems (arxiv.org)

Training Mixed-Monotone Neural Networks for Verification Without Set Propagation (arxiv.org)

inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action (arxiv.org)

SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges (arxiv.org)

StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion (arxiv.org)

SLoSa: Small, Low-Power, and Safe Foundation Models for Robotic Task Planning (arxiv.org)

MOER: Mix-Policy Optimization under Expert Prefix Guidance with Selective Rollback (arxiv.org)

Predictable performance is suboptimal, and what it means for model routing (arxiv.org)

Drift Says When, Budget Says How Much: Rate-Controlled KV Re-selection for Long-Form Multimodal Generation (arxiv.org)

Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale (arxiv.org)

RheOPT: Few-Shot Non-Newtonian Flow Prediction via Newtonian Pretraining of RheOFormer (arxiv.org)