8 papers
Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding
Bo Zhang, Wenxin Wang, Feng Chen +4
Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. How…
Agentic Collaborative Cognition for Zero-Shot 3D Understanding
Wenxin Wang, Bo Zhang, Feng Chen +4
Recent advancements have explored agentic zero-shot 3D understanding by reformulating it as video keyframe understanding with Multimodal Large Language Models (MLLMs). However, exi…
PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models
Xianghui Wang, Feng Chen, Wenbo Zhang +4
Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency. While existi…
PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback
Chunji Lv, Jiaxi Ye, Yuchen Jiang +2
Achieving fully automated, physically plausible 3D motion synthesis is a core objective in graphics and generative AI. However, configuring complex environmental force fields still…
Training-free Motion Factorization for Compositional Video Generation
Zixuan Wang, Ziqin Zhou, Feng Chen +4
Compositional video generation aims to synthesize multiple instances with diverse appearance and motion. However, current approaches mainly focus on binding semantics, neglecting t…
Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation
Xiaochuan Li, Guoguang Du, Runze Zhang +11
Scaling laws have validated the success and promise of large-data-trained models in creative generation across text, image, and video domains. However, this paradigm faces data sca…
PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
Chunji Lv, Zequn Chen, Donglin Di +5
Despite advances in physics-based 3D motion synthesis, current methods face key limitations: reliance on pre-reconstructed 3D Gaussian Splatting (3DGS) built from dense multi-view…
RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
Haoran Hao, Jiaming Han, Changsheng Li +2
The development of large language models (LLMs) has significantly enhanced the capabilities of multimodal LLMs (MLLMs) as general assistants. However, lack of user-specific knowled…