1 citations · 1 across the 6 of their papers we have counts for
7 papers
A Low-Latency Interactive System for Real-Time Video Understanding Based on VLMs
Punan Dai, Jun Xu, Bingcong Lu +4
Vision-language models are extending video understanding from offline clip analysis to continuous interactive streaming, but most research still emphasizes model capability rather…
Decoupled Self-Forcing Distillation for Streaming Talking Head Generation
Yanru An, Ruiyan Wang, Wenwu Wei +7
Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite directions: end-to-end methods condit…
Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding
Donghui Feng, Fengxi Zhang, Changsheng Gao +6
Distributed deployment of large vision foundation models often partitions a ViT backbone and exchanges intermediate token features between computing nodes, making efficient feature…
MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings
Yuelin Hu, Jun Xu, Bingcong Lu +4
Enterprise meeting environments require AI assistants that handle diverse operational tasks, from rapid fact checking during live discussions to cross meeting analysis for strategi…
Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference
Jianglong Li, Jun Xu, Bingcong Lu +4
The demand for immersive and interactive communication has driven advancements in 3D video conferencing, yet achieving high-fidelity 3D talking face representation at low bitrates…
Content-Aware Mamba for Learned Image Compression
Yunuo Chen, Zezheng Lyu, Bing He +6
Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts conten…
Linear Attention Modeling for Learned Image Compression
Donghui Feng, Zhengxue Cheng, Shen Wang +4
Recent years, learned image compression has made tremendous progress to achieve impressive coding efficiency. Its coding gain mainly comes from non-linear neural network-based tran…