avatar

Jiaming Han

be simple, be happy

Jiaming Han
PhD Student · MMLab, The Chinese University of Hong Kong
Scholar Github Email WeChat Twitter

Biography

I am a third-year PhD student of MMLab@CUHK advised by Prof. Xiangyu Yue. Before that, I received my Master and Bachelor degree from Wuhan University and Central South University, respectively. I also interned at Bytedance Seed, Shanghai AI Lab and Tencent YouTu Lab.

My research builds toward a unified intelligent system through multimodal foundation models—from efficient multimodal alignment that binds diverse modalities to language (LLaMA-Adapter, OneLLM), to unifying multimodal understanding and generation within a single autoregressive model (Tar, BitDance), and now toward world models, with the long-term goal of building a unified large model that perceives, generates, reasons, and acts in the world.

I expect to graduate in Summer 2027 and am actively seeking full-time job opportunities. Feel free to contact me via Email and Wechat.

Selected Publications

Multimodal Generation & Unified Models
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Yuang Ai*, Jiaming Han*, Shaobin Zhuang*, Weijia Mao, Xuefeng Hu, Ziyan Yang, Zhenheng Yang, Huaibo Huang, Xiangyu Yue, Hao Chen
Project Page Paper Models Demo
UniWeTok: An Unified Binary Tokenizer with Codebook Size 2^128 for Unified Multimodal Large Language Model
UniWeTok: An Unified Binary Tokenizer with Codebook Size 2128 for Unified Multimodal Large Language Model
Shaobin Zhuang*, Yuang Ai*, Jiaming Han*, Weijia Mao, Xiaohui Li, Fangyikang Wang, Xiao Wang, Yan Li, Shanchuan Lin, Kun Xu, Zhenheng Yang, Huaibo Huang, Xiangyu Yue, Hao Chen, Yali Wang
Paper
Bridge: Growing Visual Generative Capacity for Pre-Trained MLLMs
Bridge: Growing Visual Generative Capacity for Pre-Trained MLLMs
Hanyu Wang*, Jiaming Han*, Ziyan Yang, Qi Zhao, Shanchuan Lin, Xiangyu Yue, Abhinav Shrivastava, Zhenheng Yang, Hao Chen
Project Page Paper Code
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Jiaming Han, Hao Chen, Yang Zhao, Hanyu Wang, Qi Zhao, Ziyan Yang, Hao He, Xiangyu Yue, Lu Jiang
NeurlPS 2025 Project Page Paper Code Models Demo
Long Video & RAG & Embodied Reasoning
CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
Shilin Yan, Jiaming Han, Joey Tsai, Hongwei Xue, Rongyao Fang, Lingyi Hong, Ziyu Guo, Ray Zhang
Paper Code
Multimodal Long Video Modeling Based on Temporal Dynamic Context
Multimodal Long Video Modeling Based on Temporal Dynamic Context
Haoran Hao*, Jiaming Han*, Yiyuan Zhang, Xiangyu Yue
Project Page Paper Code
Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
Yunhai Feng, Jiaming Han, Zhuoran Yang, Xiangyu Yue, Sergey Levine, Jianlan Luo
CoRL 2025 Project Page Paper Code
Retrieval-Augmented Personalization for Multimodal Large Language Models
Retrieval-Augmented Personalization for Multimodal Large Language Models
Haoran Hao*, Jiaming Han*, Changsheng Li, Yu-Feng Li, Xiangyu Yue
CVPR 2025 Project Page Paper Code
Multimodal Alignment
OneLLM: One Framework to Align All Modalities with Language
OneLLM: One Framework to Align All Modalities with Language
Jiaming Han, Kaixiong Gong, Yiyuan Zhang, Jiaqi Wang, Kaipeng Zhang, Dahua Lin, Yu Qiao, Peng Gao, Xiangyu Yue.
CVPR 2024 Project Page Paper Code Demo
ImageBind-LLM: Multi-modality Instruction Tuning
ImageBind-LLM: Multi-modality Instruction Tuning
Jiaming Han*, Renrui Zhang*, Wenqi Shao*, Peng Gao*, Peng Xu*, Han Xiao*, Kaipeng Zhang, Chris Liu, Song Wen, Ziyu Guo, Xudong Lu, Shuai Ren, Yafei Wen, Xiaoxin Chen, Xiangyu Yue, Hongsheng Li, Yu Qiao.
Paper Code Demo
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
Peng Gao*, Jiaming Han*, Renrui Zhang*, Ziyi Lin*, Shijie Geng, Aojun Zhou, Wei Zhang, Pan Lu, Conghui He, Xiangyu Yue, Hongsheng Li, Yu Qiao.
Paper Code Demo
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Renrui Zhang*, Jiaming Han*, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, Peng Gao, Yu Qiao.
ICLR 2024 Paper Code Demo
Object Detection
Few-Shot Object Detection via Variational Feature Aggregation
Few-Shot Object Detection via Variational Feature Aggregation
Jiaming Han, Yuqiang Ren, Jian Ding, Ke Yan, Gui-Song Xia.
AAAI 2023 Paper Code
Expanding Low-Density Latent Regions for Open-Set Object Detection
Expanding Low-Density Latent Regions for Open-Set Object Detection
Jiaming Han, Yuqiang Ren, Jian Ding, Xingjia Pan, Ke Yan, Gui-Song Xia.
CVPR 2022 Paper Code
ReDet: A Rotation-Equivariant Detector for Aerial Object Detection
ReDet: A Rotation-Equivariant Detector for Aerial Object Detection
Jiaming Han, Jian Ding, Nan Xue, Gui-Song Xia.
CVPR 2021 Project Paper Code Poster Slide
Align Deep Features for Oriented Object Detection
Align Deep Features for Oriented Object Detection
Jiaming Han, Jian Ding, Jie Li, Gui-Song Xia.
TGRS 2021 Paper Code

Experience

06/2024 - Present
Bytedance Seed

Unified MLLM with Dr. Lu Jiang

10/2022 - 02/2024
Shanghai AI Lab

Multimodal LLM with Dr. Peng Gao

05/2021 - 05/2022
Tencent YouTu Lab

Object Detection with Dr. Yuqiang Ren

Educations

09/2023 - Present
PhD. The Chinese University of Hong Kong
09/2019 - 06/2022
M.E. Wuhan University
09/2015 - 06/2019
B.E. Central South University

Activities

  • Reviewer of CVPR’21-24, ICCV’21-23, NIPS’23, ICLR’24, WACV’22, ECCV’22-24, AAAI’23-24
  • Reviewer of TPAMI, IJCV, TIP, ISPRS, TGRS, TNNLS