Publications (9)
AI for Service: Proactive Assistance with AI Glasses
Zichen Wen, Yiyu Wang, Chenfei Liao +10
In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-t…
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Haodong Li, Tianfei Ren, Xiaoxiao Ma +25
The paper presents VideoCoCo, a system that generates physically consistent videos by having a coding agent produce executable Blender code that defines the scene and its dynamics,…
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
Yiyu Wang, Xuyang Liu, Xiyan Gui +5
Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-ti…
Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
Junlong Ke, Zichen Wen, Boxue Yang +6
Native unified multimodal models, which integrate both generative and understanding capabilities, face substantial computational overhead that hinders their real-world deployment.…
OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing
Zebang Cheng, Shuimu Chen, Boxue Yang +7
Reinforcement learning for multimodal large language models (MLLMs) is often hindered by severe reward sparsity in complex reasoning tasks. This challenge is particularly pronounce…
EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
Zichen Wen, Boxue Yang, Junlong Ke +5
Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most vide…
ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning
Zhuolong Li, Boxue Yang, Haopeng Chen
Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or n…
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
Zichen Wen, Boxue Yang, Shuang Chen +30
We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent…
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Chaoyue Li, Boxue Yang, Shengyao Zhou +3
4D dynamic scene understanding requires grounding language to a persistent worldline that binds identity, metric 3D motion, and synchronized multi-view 2D projections. Existing par…