AI News

Transparent Information Flow Modeling for Role-Aware AI Act Assessment (arxiv.org)

ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context (arxiv.org)

Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev (arxiv.org)

WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search (arxiv.org)

CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives (arxiv.org)

DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting (arxiv.org)

GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines (arxiv.org)

Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation (arxiv.org)

Growing and Transferring Pathways for LLM Reinforcement Learning (arxiv.org)

Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing (arxiv.org)

Large language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework (arxiv.org)

Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance (arxiv.org)

Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems (arxiv.org)

Structural Baselines Matter for Agent Failure Detection and Attribution (arxiv.org)

Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision (arxiv.org)

SLEM: Spectrum-Aware Latent Expert Merging (arxiv.org)

PATMT2: Two-stage domain adaptation for multilingual patent translation (arxiv.org)

StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning (arxiv.org)

CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing (arxiv.org)

AutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms (arxiv.org)

VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric (arxiv.org)

ARMED: Adaptive Retrieval-Augmented Medication Recommendation (arxiv.org)

Queue-Aware Token Communications: Bridging AI Representation and Wireless Service (arxiv.org)

Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings (arxiv.org)

Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios (arxiv.org)

Neos: Learning to Interleave Search and Visual Reasoning (arxiv.org)

On the Dynamics of Delayed Generalization in Linear Models (arxiv.org)

Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering (arxiv.org)

Understanding and Reducing Misalignment in Persuasion Optimization (arxiv.org)

Parameter-Efficient Temporal Domain Generalization (arxiv.org)

LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers (arxiv.org)

DWI Connectome-based Sex Classification in Young using Supervised Variational Autoencoder (arxiv.org)

The Sharp Directions Are Against You: Curvature Analysis of Activation Steering (arxiv.org)

Heterogeneous Agentic Coevolution (arxiv.org)

Reflected Proximal Dynamics for Accelerated High-Accuracy Log-Concave Sampling (arxiv.org)

EvolvAttack: Backdooring self Evolving VLM Agents (arxiv.org)

Framework for an AI-Ready ARPES Community Database (arxiv.org)

PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces (arxiv.org)

Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models (arxiv.org)

UDHRBench: Benchmarking Human Rights in Large Language Models (arxiv.org)

To Defer or Not to Defer? Online Learning with LLMs and Congested Experts (arxiv.org)

RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition (arxiv.org)

Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena (arxiv.org)

Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap (arxiv.org)

Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams (arxiv.org)

Optimization for One, Feasibility for Most: Decoupling Optimization from Feasibility in Chance-Constrained Programs (arxiv.org)

ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer (arxiv.org)

Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry (arxiv.org)

scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data (arxiv.org)

TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents (arxiv.org)