12 citations · 15 across the 17 of their papers we have counts for
20 papers
Beyond a single latent space: a dual-latent world model for long-horizon planning
Delin Zhao, Zhengrong Yue, Shaobin Zhuang +6
Latent world models often struggle with long-horizon planning despite accurate short-term predictions. Recursive rollouts accumulate errors, while distance concentration in high-di…
WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
Yiwei Guo, Shaobin Zhuang, Zhipeng Huang +4
Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict betwe…
BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
Shaobin Zhuang, Yuang Ai, Jiaming Han +7
Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations t…
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Yuang Ai, Jiaming Han, Shaobin Zhuang +8
We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy binary latents, BitDance lets…
UniWeTok: An Unified Binary Tokenizer with Codebook Size for Unified Multimodal Large Language Model
Shaobin Zhuang, Yuang Ai, Jiaming Han +12
Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generat…
UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
Zhengrong Yue, Haiyu Zhang, Xiangyu Zeng +7
Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing…
LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
Xiaohui Li, Shaobin Zhuang, Shuo Cao +6
Generative models for Image Super-Resolution (SR) are increasingly powerful, yet their reliance on self-attention's quadratic complexity (O(N^2)) creates a major computational bott…
WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
Shaobin Zhuang, Yiwei Guo, Canmiao Fu +7
Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios and reconstruction f…
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin
Fangyikang Wang, Hubery Yin, Lei Qian +9
The diffusion models (DMs) have demonstrated the remarkable capability of generating images via learning the noised score function of data distribution. Current DM sampling techniq…
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
Fangyikang Wang, Hubery Yin, Shaobin Zhuang +7
Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into vari…
Video-GPT via Next Clip Diffusion
Shaobin Zhuang, Zhipeng Huang, Ying Zhang +6
GPT has shown its remarkable success in natural language processing. However, the language sequence is not sufficient to describe spatial-temporal details in the visual world. Alte…
V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
Zhengrong Yue, Shaobin Zhuang, Kunchang Li +2
Despite the recent advancement in video stylization, most existing methods struggle to render any video with complex transitions, based on an open style description of user query.…
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
Shaobin Zhuang, Yiwei Guo, Yanbo Ding +7
Diffusion models have driven the advancement of vision generation over the past years. However, it is often difficult to apply these large models in downstream tasks, due to massiv…
WeGen: A Unified Model for Interactive Multimodal Generation as We Chat
Zhipeng Huang, Shaobin Zhuang, Canmiao Fu +7
Existing multimodal generative models fall short as qualified design copilots, as they often struggle to generate imaginative outputs once instructions are less detailed or lack th…
Get In Video: Add Anything You Want to the Video
Shaobin Zhuang, Zhipeng Huang, Binxin Yang +7
Video editing increasingly demands the ability to incorporate specific real-world instances into existing footage, yet current approaches fundamentally fail to capture the unique v…
DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations
Xiaohui Li, Yihao Liu, Shuo Cao +6
Diffusion models have demonstrated exceptional capabilities in image restoration, yet their application to video super-resolution (VSR) faces significant challenges in balancing fi…
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
Yiwei Guo, Shaobin Zhuang, Kunchang Li +2
Vision-language foundation models (such as CLIP) have recently shown their power in transfer learning, owing to large-scale image-text pre-training. However, target domain data in…
MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration
Yanbo Ding, Shaobin Zhuang, Kunchang Li +3
Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To…
Vlogger: Make Your Dream A Vlog
Shaobin Zhuang, Kunchang Li, Xinyuan Chen +4
In this work, we present Vlogger, a generic AI system for generating a minute-level video blog (i.e., vlog) of user descriptions. Different from short videos with a few seconds, vl…
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Xinyuan Chen, Yaohui Wang, Lingjun Zhang +7
Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shot-level") depicting…