AI News

Channel-Adaptive Region Adjacency Graph Carriers for Semantic Image Communication (arxiv.org)

AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory (arxiv.org)

Learning Multi-Agent Task Assignment and Navigation in the Factory: from Simulation to Real Robots (arxiv.org)

Sharing standardized image-derived data in computational pathology using DICOM (arxiv.org)

Enhancing Large Language Model-Based Systems for End-to-End Circuit Analysis Problem Solving (arxiv.org)

Perceptual Reality Transformer: What Must an Illustration Preserve? (arxiv.org)

JSolver: Joint Spectrum Estimation and Multi-Material Decomposition from Single-Energy CT Projections (arxiv.org)

Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps (arxiv.org)

ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation (arxiv.org)

Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation (arxiv.org)

BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Sounds (arxiv.org)

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers (arxiv.org)

EventVL: Understand Event Streams via Multimodal Large Language Model (arxiv.org)

Balancing Global Quality and Pronoun-Specific Feedback for Context-Aware Machine Translation (arxiv.org)

From Voice to Value: Leveraging AI to Enhance Spoken Online Reviews on the Go (arxiv.org)

Zonal RL-RRT: Integrated RL-RRT Path Planning with Collision Probability and Zone Connectivity (arxiv.org)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer (arxiv.org)

K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments (arxiv.org)

Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving (arxiv.org)

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents (arxiv.org)

Aerial Wildfire Suppression Planning with a Hybrid CNN-Cellular Automata Fire Model (arxiv.org)

Enabling Population-Based Architectures for Neural Combinatorial Optimization (arxiv.org)

Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognition (arxiv.org)

Non-Asymptotic Global Convergence of PPO-Clip (arxiv.org)

Random matrix theory of sparse neuronal networks with heterogeneous timescales (arxiv.org)

DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understanding (arxiv.org)

The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference (arxiv.org)

Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City (arxiv.org)

CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection (arxiv.org)

Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models (arxiv.org)

MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use (arxiv.org)

Privileged observations enable rapid and reliable policy discovery directly in the physical world (arxiv.org)

DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals (arxiv.org)

Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations (arxiv.org)

Efficient On-Device Agents via Adaptive Context Management (arxiv.org)

Exact Spin Elimination for Quadratic and k-Local Ising Optimization (arxiv.org)

Programs as Singularities (arxiv.org)

CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback (arxiv.org)

Concept drift mitigation through community and spectral graph analysis for the detection of cyberattacks in network traffic (arxiv.org)

GRADE: Graph Representation of LLM Agent Dependency and Execution (arxiv.org)

SDUs DAISY: A Benchmark for Danish Culture (arxiv.org)

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges (arxiv.org)

Learning Human-Like Badminton Skills for Humanoid Robots (arxiv.org)

AbFlow : End-to-end Paratope-Centric Antibody Design by Interaction Enhanced Flow Matching (arxiv.org)

UniRank: Unified Rank Allocation for Low-Rank LLM Compression (arxiv.org)

Disparate Impact in Synthetic Data Generation (arxiv.org)

Dreaming in Code for Curriculum Learning in Open-Ended Worlds (arxiv.org)

Hybrid Feedback-Guided Optimal Learning for Wireless Interactive Panoramic Scene Delivery (arxiv.org)

Architecture--Optimization Co-Design for Physics-Informed Neural Networks via Layer-wise Coordinate Adaptation and Gradient Conflict Resolution (arxiv.org)

Learning Steerable Clarification Policies with Collaborative Self-play (arxiv.org)