activity
20242026
collaborators

10 papers

cs.CV2026

VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding

Zhihao He, Tieyuan Chen, Kangyu Wang +6

Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this…

cs.CV2025

Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens

Ziran Qin, Youru Lv, Mingbao Lin +4

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image gen…

cs.CV2025

Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers

Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +5

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for visual generation. Recent observations reveal \emph{Massive Activations} (MAs) in their internal feat…

cs.CL2025

DND: Boosting Large Language Models with Dynamic Nested Depth

Tieyuan Chen, Xiaodong Chen, Haoxing Chen +3

We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifi…

cs.CV2025

Enhancing Video Large Language Models with Structured Multi-Video Collaborative Reasoning

Zhihao He, Tianyao He, Yun Xu +5

Despite the prosperity of the video language model, the current pursuit of comprehensive video reasoning is thwarted by the inherent spatio-temporal incompleteness within individua…

cs.CV2025

Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning

Tieyuan Chen, Huabin Liu, Yi Wang +8

Video Question Answering (VideoQA) aims to answer natural language questions based on the given video, with prior work primarily focusing on identifying the duration of relevant se…