AI News

Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference (arxiv.org)

ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models (arxiv.org)

Contrastive Neural Algorithmic Reasoning for Graph Coloring (arxiv.org)

When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning (arxiv.org)

Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks (arxiv.org)

Consistency Training Can Entrench Misalignment (arxiv.org)

Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models (arxiv.org)

BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions (arxiv.org)

Inducing Reasoning Primitives from Agent Traces (arxiv.org)

AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification (arxiv.org)

Binary Road Surface Classification Using Machine Learning on Production Vehicle Signals During Cruising (arxiv.org)

Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models (arxiv.org)

What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents (arxiv.org)

Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing (arxiv.org)

Learning Coherent Representations: A Topological Approach to Interpretability (arxiv.org)

WISE-HAR: A Generalizable Ensemble Deep Learning Framework for WiFi-Based Human Activity Recognition (arxiv.org)

RRISE: Robust Radius Inference via a Surrogate Estimator (arxiv.org)

RESCAST-100K: A Comprehensive Dataset for Cross-Domain Residential Load and Indoor Temperature Forecasting (arxiv.org)

ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents (arxiv.org)

RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases (arxiv.org)

Solipsistic Superintelligence is Unlikely to be Cooperative (arxiv.org)

CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection (arxiv.org)

FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments (arxiv.org)

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees (arxiv.org)

Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models (arxiv.org)

AI-Generated Traces for Novice Programmers: Learning Effects and Learner Differences in a Multi-Institutional Study (arxiv.org)

A Nonmonotone Gradient-Based Algorithm for Symmetric Nonnegative Matrix Factorization and Graph Clustering (arxiv.org)

Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning (arxiv.org)

Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering (arxiv.org)

Uncertainty-Aware Clarification in LLM Agents with Information Gain (arxiv.org)

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents (arxiv.org)

Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation (arxiv.org)

LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks (arxiv.org)

What Makes Interaction Trajectories Effective for Training Terminal Agents? (arxiv.org)

Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic (arxiv.org)

Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition (arxiv.org)

Conditional Latent Diffusion Model with Fourier-based Motion Modelling for Virtual Population Synthesis (arxiv.org)

Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence Review (arxiv.org)

Constitutional On-Policy Safe Distillation (arxiv.org)

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward (arxiv.org)

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval (arxiv.org)

The DeepSpeak-Agentic Dataset (arxiv.org)

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)

Evaluating LLMs' Effectiveness on Real-World Consumer Device Repair Questions (arxiv.org)

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents (arxiv.org)

Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making (arxiv.org)

HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models (arxiv.org)

WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts (arxiv.org)

Enhancing Protein-Protein Interaction Prediction with Hierarchical Motif-based Multimodal Protein Embedding (arxiv.org)

Towards Compact Autonomous Driving Perception with Balanced Learning and Multi-sensor Fusion (arxiv.org)