AI News

Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers (arxiv.org)

PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window (arxiv.org)

The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation (arxiv.org)

TriSP: Tri-Signal Structured Pruning for Large Language Models (arxiv.org)

AI-Assisted Causal Inference and Mediation Analyses of Environmental and Psychosocial Determinants of Subjective Cognitive Difficulties in the All of Us Research Program (arxiv.org)

Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks (arxiv.org)

Traceable LLM Reasoning for Fake-Order Fraud Detection (arxiv.org)

Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits (arxiv.org)

Falsifiable Commitment Planning for Self-Correcting Web Agents (arxiv.org)

Retrieval-Augmented Generation of Ontologies from Relational Databases (arxiv.org)

CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference (arxiv.org)

TLRNet: Estimating Individual Treatment Effect based on Local Information and Single Learner Structure (arxiv.org)

Debiased Machine Learning: Identification, Estimation, and Shape Constraints (arxiv.org)

MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models (arxiv.org)

EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis (arxiv.org)

Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization (arxiv.org)

Distributional Split Criteria for Random Forests: Extensions, Shrinkage, and the Robustness of Mean Splitting (arxiv.org)

Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise (arxiv.org)

Robust Conformalized Selection with Noisy Responses (arxiv.org)

Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model (arxiv.org)

Amortized Bayesian Causal Discovery of Extended Factor Graphs (arxiv.org)

Two-Timescale Hierarchical Reinforcement Learning for Resilient Operations (arxiv.org)

Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness (arxiv.org)

Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities (arxiv.org)

GNN-based Multi-Agent Control of Traffic Shockwaves in Sparse Vehicular Ad-hoc Networks (arxiv.org)

Lexical discovery in unknown environments orchestrated by Large Language Models (arxiv.org)

Scoping Review of AI, Metrology, and ESG in the Semiconductor Sector: Implications for Safe and Sustainable by Design (SSbD) (arxiv.org)

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models (arxiv.org)

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference (arxiv.org)

MIME: Multimodal Interactive Motion Encoder (arxiv.org)

TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs (arxiv.org)

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features (arxiv.org)

Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search (arxiv.org)

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation (arxiv.org)

RoleMix: Unifying Sequential and Non-Sequential Features via Semantic Tokenization for Post-Click Conversion Rate Prediction (arxiv.org)

HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation (arxiv.org)

Decision trees, Frobenius traces, and Weierstrass coefficients of elliptic curves (arxiv.org)

Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior Approach (arxiv.org)

ARdena: Scenario-driven control of real-time LLM agents (arxiv.org)

FedSLIM: Privacy-Preserving Federated MDL-Based Descriptive Pattern Mining Across Data Silos (arxiv.org)

A Fixed-Effects Causal Forest for Staggered Adoption, with an Application to Medicaid Expansion (arxiv.org)

Epistemic Norms for AI Safety and Alignment Research (arxiv.org)

ADAGE: A Language-Agnostic Pipeline for Analogical Reasoning Evaluation (arxiv.org)

GeoDecider: An Evidence-Grounded Agent for Geological Interpretation via Deliberative Reasoning (arxiv.org)

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement (arxiv.org)

CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback (arxiv.org)

Imprompt: A Language Framework for Prompt Programming (arxiv.org)

Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment (arxiv.org)

HydroAgent: Formalizing Forecaster Expertise into Skill-Orchestrated Flood Forecasting Workflows (arxiv.org)

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model (arxiv.org)