AI News

Graph Edit Distance Formulation for the Vehicle Routing Problem: Theory and Analysis (arxiv.org)

CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropout (arxiv.org)

Trust Region On-Policy Distillation (arxiv.org)

"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise (arxiv.org)

OmniEEG-Bench: A Standardized Evaluation Benchmark for EEG Foundation Models (arxiv.org)

Joint Agent Memory and Exploration Learning via Novelty Signals (arxiv.org)

LeARN: Learnable and Adaptive Representations for Nonlinear Dynamics in System Identification (arxiv.org)

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning (arxiv.org)

Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance (arxiv.org)

Learning to Reduce Search Space for Generalizable Neural Routing Solver (arxiv.org)

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters (arxiv.org)

Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs (arxiv.org)

Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecasting (arxiv.org)

Optimal Transport-based Permutation-Invariant Bayesian Optimization of Offshore Wind Farm Layouts (arxiv.org)

Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations (arxiv.org)

Everywhere Learning: Artificial Intelligence with Pointwise Constraints (arxiv.org)

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer (arxiv.org)

Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems: Method and Industrial Evidence-Quality Audit (arxiv.org)

naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement (arxiv.org)

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs (arxiv.org)

Interpretability in Deep Time Series Models Demands Semantic Alignment (arxiv.org)

Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance (arxiv.org)

Low-Resource Safety Failures Are Action Failures, Not Representation Failures (arxiv.org)

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models (arxiv.org)

TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination (arxiv.org)

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning (arxiv.org)

Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization (arxiv.org)

Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents (arxiv.org)

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time (arxiv.org)

Algebraic anti-unification (arxiv.org)

Continuous Data Assimilation with Learned Surrogate Dynamics (arxiv.org)

TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications (arxiv.org)

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning (arxiv.org)

Logit Distillation on Manifolds: Mapping by Learning (arxiv.org)

Practical Aspects on Solving Differential Equations Using Deep Learning: A Primer (arxiv.org)

Stochastic convergence of parallel asynchronous adaptive first-order methods (arxiv.org)

Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation (arxiv.org)

Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models (arxiv.org)

Analysis of Ethnic Disparities in Autism Spectrum Disorder among Toddlers (arxiv.org)

DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning (arxiv.org)

Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee (arxiv.org)

Characterizing the Effect of Noise in Language Generation in the Limit (arxiv.org)

Project SPARROW and the Future of Conservation Technology (arxiv.org)

Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling (arxiv.org)

3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code (arxiv.org)

CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection (arxiv.org)

AI From the Margins (AIM): Rethinking Participatory AI Design Through the Lived Experience of Minoritized Communities (arxiv.org)

Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations (arxiv.org)

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models (arxiv.org)

Exploiting Similarities in A/B Testing with Off-Policy Estimation (arxiv.org)