AI News

Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition (arxiv.org)

Training seeds and model-selection stability in recommender-system evaluation (arxiv.org)

When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models (arxiv.org)

TaRA: Training-Aware Low-Rank Adaptation Initialization (arxiv.org)

Humanoid Safe Stop via Learned Stoppability Value (arxiv.org)

Poisoning Attacks on the PGM-index (arxiv.org)

Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning (arxiv.org)

Addressing Trust in AI Systems through Education: A Didactic Perspective (arxiv.org)

Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression (arxiv.org)

Towards One-for-All Robustness Across a Continuum of Threat Levels (arxiv.org)

Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models (arxiv.org)

Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment (arxiv.org)

Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking (arxiv.org)

Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts (arxiv.org)

PolERo: Studying Political Evasion in Romanian (arxiv.org)

MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts (arxiv.org)

NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning (arxiv.org)

Towards a Foundational Ontology for Identifying and Resolving Contradictions in Dialogue-based Human-Robot Interactions (arxiv.org)

Subcellularly Resolved Single-Cell Embedding Learning with Transcriptomic data, Protein Structure and Localization Information (arxiv.org)

AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers (arxiv.org)

ORB-SVM : An Innovative Hybrid Framework for Efficient Brain Tumor Detection from MRI Scans (arxiv.org)

What Is Worth Representing? Representational Empowerment for Continual Model Construction (arxiv.org)

DiffIE: Diffusion-based Open Information Extraction (arxiv.org)

SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment (arxiv.org)

VoRTeC: Taming Foundation Flow for One-step Real time Video Compression (arxiv.org)

RouteGraph-Mona: Confusion-Aware Routing Fine-Tuning for Mineral Image Classification (arxiv.org)

Auditory Illusion Benchmark for Large Audio Language Models (arxiv.org)

Do Large Language Models Capture the Diversity in their Training Data? (arxiv.org)

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation (arxiv.org)

CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation (arxiv.org)

Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics (arxiv.org)

DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion and Action Space (arxiv.org)

SAUF-Net: Structure--Appearance Representation Learning with Uncertainty Feedback for Semi-Supervised Medical Image Segmentation (arxiv.org)

InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models (arxiv.org)

Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imaging (arxiv.org)

SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework (arxiv.org)

OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction (arxiv.org)

Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation (arxiv.org)

OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations (arxiv.org)

C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees (arxiv.org)

text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation (arxiv.org)

MeanField Surrogate Modeling for Scalable Runtime Scheduling of Concurrent Heterogeneous AI Inference on Shared GPUs (arxiv.org)

Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models (arxiv.org)

Git4Data: Database-Native Version Control for AI Agents (arxiv.org)

Objective-Behavior Alignment: Diagnostics for MORL Policy Selection (arxiv.org)

Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning (arxiv.org)

Nonasymptotic CLT and Error Bounds for Linear Two-Time-Scale Stochastic Approximation (arxiv.org)

Double-Bounded Nonlinear Optimal Transport for Size Constrained Min Cut Clusterin (arxiv.org)

Monotonic anomaly detection (arxiv.org)

Action abstractions for amortized sampling (arxiv.org)