Donglin Bai — accepted AI-conference papers

2026

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

Chendong Wang, Donglin Bai, Yifan Yang, Xiao Jin, Anlan Zhang, Rui Wang +8

ICML 2026poster

We present $\textit{Video-in-the-Loop}$ (ViTL), a two-stage long-video QA framework that preserves a fixed token budget by first $\textit{localizing}$ question-relevant interval(s) with a low-fps skim and then $\textit{answering}$ via span-aware reallocation of visual tokens at higher effective fram…

Cited by 3 Source ↗Scholar ↗

2025

StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition

Xin Ding, Hao Wu, Yifan Yang, Shiqi Jiang, Qianxi Zhang, Donglin Bai +2

ICCV 2025poster

With the rise of real-world human-AI interaction applications, such as AI assistants, the need for Streaming Video Dialogue is critical. To address this need, we introduce StreamMind, a video LLM framework that achieves ultra-FPS streaming video processing (100 fps on a single A100) and enables proa…

Cited by 0 Source ↗PDF ↗Scholar ↗