collaborators

5 papers

cs.CV2025

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Anlin Zheng, Xin Wen, Xuanyang Zhang +5

In this work, we present a novel direction to build an image tokenizer directly on top of a frozen vision foundation model, which is a largely underexplored area. Specifically, we…

cs.CV2025

Hita: Holistic Tokenizer for Autoregressive Image Generation

Anlin Zheng, Haochen Wang, Yucheng Zhao +4

Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, becaus…

cs.CV2025

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

Haochen Wang, Yucheng Zhao, Tiancai Wang +3

The rapid development of Large Multimodal Models (LMMs) for 2D images and videos has spurred efforts to adapt these models for interpreting 3D scenes. However, the absence of large…

eess.IV2025

Neighboring Slice Noise2Noise: Self-Supervised Medical Image Denoising from Single Noisy Image Volume

Langrui Zhou, Ziteng Zhou, Xinyu Huang +3

In the last few years, with the rapid development of deep learning technologies, supervised methods based on convolutional neural networks have greatly enhanced the performance of…

cs.CV2024

Reconstructive Visual Instruction Tuning

Haochen Wang, Anlin Zheng, Yucheng Zhao +4

This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals. In contrast to co…