Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document …
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
Hierarchical Evidence-Driven Reasoning for Long Document Understanding
MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-…
Measuring What Matters: A Unified Evaluation Framework for GNN Explainability
Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforceme…
Can temporal article-level credibility signals improve domain-level credibility predictio…
EEG-SpikeAgent: Agentic Closed-Loop Program Synthesis for Automated EEG Spike Detection
Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Lev…
Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Ir…
Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
Language Models Represent and Transform Concepts with Shared Geometry
Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning
VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
Constrained Flow Matching via Lagrangian Dual Flows
Why Pure Reasoning is Not Enough: Nature as the Source of Mathematical Innovation
New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and …
Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems
Transferability Between Understanding and Generation in Unified Multimodal Models
MambaRefine-CD: MambaVision with Region-Boundary Temporal Refinement
MechMath Agent Team: LLM Driven Agents for Mathematical Research
Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models
Legible-by-Construction: Attention and End-to-End Transformers
AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geome…
Agentic-V2X: Small Language Model Agents for Deadline-Aware V2X Scheduling in 5G/6G Netwo…
LBR: Towards Mitigating Length Bias in Large Language Models for Recommendation
Sangam: Efficiently Serving Diffusion LLMs with the AR Stack