AI News

Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline (arxiv.org)

PAFO: Pareto Fairness Optimization for Personalized Reward Modeling (arxiv.org)

VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation (arxiv.org)

Efficient Skill Grounding via Code Refactoring with Small Language Models (arxiv.org)

UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL (arxiv.org)

Knowledge-Inclusive Adaptive Physics-Informed Neural Network for Microbial Interaction Modelling (arxiv.org)

HARP: Efficient Data Selection for Finetuning Large Language Models (arxiv.org)

BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing (arxiv.org)

DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Forecasting in Urban Transportation Systems (arxiv.org)

Cross-LLM Consistency in Inference: Evidence from Shared Interactions (arxiv.org)

OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs (arxiv.org)

SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows (arxiv.org)

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions (arxiv.org)

A Multi-modal Agentic Co-pilot for Evidence Grounded Computational Pathology (arxiv.org)

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference (arxiv.org)

PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents (arxiv.org)

Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction (arxiv.org)

Adversarial Robustness of Activation Steering in Large Language Models (arxiv.org)

Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction (arxiv.org)

EssentialGIN: a new approach for gene essentiality prediction based on graph isomorphism neural networks (arxiv.org)

EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated Learning (arxiv.org)

How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models (arxiv.org)

FunctionEvolve: Structure-Guided Symbolic Regression with LLMs (arxiv.org)

Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks (arxiv.org)

SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection (arxiv.org)

Curation of a Cardiology Interface Terminology for Highlighting Electronic Health Records using Machine Learning (arxiv.org)

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents (arxiv.org)

Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents (arxiv.org)

Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers (arxiv.org)

SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models (arxiv.org)

Decoding Naturalistic Emotion Dynamics from the Brain: An LLM-Enhanced Regression Framework (arxiv.org)

WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing (arxiv.org)

Rosetta Memory: Adaptive Memory for Cross-LLM Agents (arxiv.org)

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels (arxiv.org)

A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction (arxiv.org)

SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents (arxiv.org)

When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding (arxiv.org)

From Validator Selection to Portfolio Collection Optimization in Proof-of-Stake Blockchains (arxiv.org)

Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems (arxiv.org)

Revisiting the shutdown problem (arxiv.org)

To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation (arxiv.org)

Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies (arxiv.org)

Integrating Deep Learning Demand Forecasting with Multi-Objective Optimization for Circular Coffee Supply Chains: A Data-Driven Framework for Cost, Emissions, and Freshness Management (arxiv.org)

Benchmarking Open-Ended Multi-Agent Coordination in Language Agents (arxiv.org)

GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model (arxiv.org)

Characterizing the Discrete Geometry of ReLU Networks (arxiv.org)

scCBGM: Interpretable Single-Cell Counterfactual Editing (arxiv.org)

Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning (arxiv.org)

Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games (arxiv.org)

On the Wasserstein Geodesic Principal Component Analysis of probability measures (arxiv.org)