8 papers · 1 filter
Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation
Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +6
Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently und…
HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling
Ziran Qin, Yuchen Jiang, Mingbao Lin +4
Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. However, existing VAR models su…
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…
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…
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…
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…
Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling
Ziran Qin, Youru Lv, Mingbao Lin +4
Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR m…
Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver
Zeren Zhang, Jo-Ku Cheng, Jingyang Deng +6
Mathematical reasoning remains an ongoing challenge for AI models, especially for geometry problems that require both linguistic and visual signals. As the vision encoders of most…