ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams Paper • 2607.09759 • Published 9 days ago • 24
DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos Paper • 2605.09586 • Published May 10 • 2
Stimulating Imagination: Towards General-purpose "Something Something Placement" Paper • 2408.01655 • Published Jul 21, 2025 • 1
Generic Token Compression in Multimodal Large Language Models from an Explainability Perspective Paper • 2506.01097 • Published Jun 1, 2025 • 3
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning Paper • 2504.08837 • Published Apr 10, 2025 • 46
DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos Paper • 2605.09586 • Published May 10 • 2
ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams Paper • 2607.09759 • Published 9 days ago • 24
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs Paper • 2510.11696 • Published Oct 13, 2025 • 183
LongLive: Real-time Interactive Long Video Generation Paper • 2509.22622 • Published Sep 26, 2025 • 190
Generic Token Compression in Multimodal Large Language Models from an Explainability Perspective Paper • 2506.01097 • Published Jun 1, 2025 • 3