CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 7 days ago • 252
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Paper • 2605.10664 • Published 9 days ago • 9
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding Paper • 2603.28696 • Published Mar 30 • 6
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 342
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published Mar 20 • 351
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published Mar 26 • 156
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151