AI News

Same Quantity, Different Answer: Numerical Representation Invariance in Language Models (arxiv.org)

Trust in Edge-Enabled IoT Security: Features, Challenges and Research Directions (arxiv.org)

When Residualization Helps an Audit: Format Effects, Slice Gains, and Their Limits (arxiv.org)

PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM Contexts (arxiv.org)

Identifying Intelligent Processes via Online Sequential Testing (arxiv.org)

Magnitude Profile Pruning: Calibration-Free Structured Attention Head Removal for Transformer Compression (arxiv.org)

MGRL-RSCC: Multi-Granularity Reward Reinforcement Learning for Fine-Grained Remote Sensing Change Captioning (arxiv.org)

Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking (arxiv.org)

ADSEL: Adaptive Dual Self-Expression Learning for EEG Feature Selection via Incomplete Multi-Dimensional Emotion Labels (arxiv.org)

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey (arxiv.org)

Calibrating Lightweight Sparse Autoencoder Feature Steering (arxiv.org)

Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning (arxiv.org)

Improved Multiplayer Bandit Algorithm for Bernoulli Rewards (arxiv.org)

Three Routes to One Answer: Reconciling AIPW, TMLE, and Double Machine Learning for Applied Researchers (arxiv.org)

xWhyL: Causal Interactive Learning (arxiv.org)

Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement (arxiv.org)

HybridFlow: A 2-NFE Generative Policy for Real-Time Robotic Manipulation (arxiv.org)

Decoding Order Matters in Autoregressive Speech Synthesis (arxiv.org)

Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding (arxiv.org)

Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization (arxiv.org)

Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity (arxiv.org)

Automatic multimodal UX improvement recommendations from LLM agent user simulations (arxiv.org)

General Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems (arxiv.org)

When Agentic Trust Crosses Organizational Boundaries: Structural Externalization and a Reference Model for Trust Evidence (arxiv.org)

Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems (arxiv.org)

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling (arxiv.org)

NostrAgent: A Decentralized Identity and Delegation Architecture for Sovereign Agentic Systems (arxiv.org)

An Evolutionary Agentic Approach for Open-ended Image Quality Perception (arxiv.org)

Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling (arxiv.org)

An Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database (arxiv.org)

Enhancing Shrimp Disease Detection via Deep Learning and Data Refinement for Resilient Aquaculture (arxiv.org)

Block-Sparse Attention with Semantic-Geometric Decoupled Routing (arxiv.org)

The Law of Stop: Interruptibility, Injunctions, and the Governance of Agentic AI (arxiv.org)

The Moral Check: Strategic AI Governance for the Pacing Problem (arxiv.org)

Planning-Aligned Pretraining of BEV Representations with Sparse Action-Conditioned Targets for End-to-End Autonomous Driving (arxiv.org)

Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs (arxiv.org)

SatOV: Restoring Spatial Priors for Training-Free Open-Vocabulary Segmentation in Remote Sensing Imagery (arxiv.org)

LLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator (arxiv.org)

GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents (arxiv.org)

Authority-Preserving Evaluation of Medical Vision-Language Assistants (arxiv.org)

On The Robustness-Resolution Tradeoff In Temporal Quantization Of Event Streams (arxiv.org)

Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models (arxiv.org)

ORDER: A Fictitious-World Benchmark for Domain-Adaptive Embodied AI (arxiv.org)

Complementary rPPG-Derived and Lip-Region Frequency Cues for Talking-Face Deepfake Detection (arxiv.org)

Rethinking Streaming Video Diffusion Model: Context, Execution, and Training (arxiv.org)

Brain-to-Image Generation: Reconstructing Visual Stimuli from EEG using Generative Adversarial Networks (arxiv.org)

Performance vs Consistency: Evaluating a Foundation Model in Lung-RADS Screening (arxiv.org)

Enabling Vision and Cross-Modal Learning for Multimodal Stroke Recurrence Prediction: An Interpretable Two-Step Framework (arxiv.org)

Hi-Singers: A Comprehensive High-Quality Dataset for Expressive Audio-Driven Singing Head Synthesis (arxiv.org)

Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection (arxiv.org)