SLA: Scaling Spatial-Language-Action Model via Continual Pre-training Paper • 2611.08373 • Published 15 days ago • 60
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published Oct 13 • 53
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Paper • 2605.29707 • Published May 28 • 58
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation Paper • 2601.21420 • Published Jan 29 • 42
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives Paper • 2601.20833 • Published Jan 28 • 124
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery Paper • 2601.19325 • Published Jan 27 • 85