STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability Paper • 2606.19236 • Published 4 days ago • 9
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published 18 days ago • 122
Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation Paper • 2605.29861 • Published 24 days ago • 16
HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos Paper • 2605.17543 • Published May 19 • 13
Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS) Paper • 2605.27268 • Published 26 days ago • 13
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published Feb 13 • 246