Bohan Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Bohan Zeng has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Wentao Zhang
Peking University, Beijing, China
5 shared publications - Yuanxing Zhang
Kuaishou Technology
4 shared publications - Pengfei Wan
Kuaishou Technology, Beijing, China
3 shared publications - Xinlong Chen
Institute of Automation, Chinese Academy of Sciences
3 shared publications - Yang Shi
Peking University, Beijing, China
3 shared publications - Bin Cui
Peking University
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5972-5981
DeltaUI: Framework-Normalized UI State Transition Modeling for Multi-Task Front-End Engineering
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5972-5981
Open AccessDeltaUI: Framework-Normalized UI State Transition Modeling for Multi-Task Front-End Engineering
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4337-4346
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4337-4346
Open AccessHuman-Centric Image Captioning with Subject-Centered Spatial Understanding
- 12 September 2026
- Published by Springer Nature
- p. 451-469
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
- 12 September 2026
- Published by Springer Nature
- p. 451-469
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2770-2781
Let's Verify Math Questions Step by Step
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2770-2781
Open AccessLet's Verify Math Questions Step by Step
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10994-11003
Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10994-11003
Open AccessMavors: Multi-granularity Video Representation for Multimodal Large Language Model
- Top Cited PapersOpen Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12674-12681
EditWorld: Simulating World Dynamics for Instruction-Following Image Editing
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12674-12681
Top Cited PapersOpen AccessEditWorld: Simulating World Dynamics for Instruction-Following Image Editing
- 20 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (6) , 6034-6046
Spatio-Temporal Energy-Guided Diffusion Model for Zero-Shot Video Synthesis and Editing
Diffusion-based generative models have exhibited considerable success in conditional video synthesis and editing. Nevertheless, prevailing video diffusion models primarily rely on conditioning with specific input modalities, predominantly text, restricting their adaptability to alternative modalities without necessitating retraining of modality-specific components. In this work, we present ENERGYVID, a universal spatio-temporal Energy-guided Video Diffusion model designed for zero-shot video synthesis and editing across diverse conditions. Specifically, we leverage off-the-shelf pre-trained networks to construct generic energy functions, guiding the generation process under specific conditions without the need for retraining. To precisely capture temporal dynamics related to motion conditions (e.g., pose sequences), we introduce a novel kernel Maximum Mean Discrepancy (MMD)-based energy function, which minimizes the global distribution discrepancy between the conditioning input and the generated video. Our extensive qualitative and quantitative experiments demonstrate that our algorithm consistently produces high-quality results across a wide range of motion and non-motion conditions, including text, face ID, style, poses, depths, sketches, canny edges, and segmentation maps, in the context of zero-shot video synthesis and editing. We will release source code upon acceptance of the paper.
- 20 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (6) , 6034-6046
Spatio-Temporal Energy-Guided Diffusion Model for Zero-Shot Video Synthesis and Editing
Diffusion-based generative models have exhibited considerable success in conditional video synthesis and editing. Nevertheless, prevailing video diffusion models primarily rely on conditioning with specific input modalities, predominantly text, restricting their adaptability to alternative modalities without necessitating retraining of modality-specific components. In this work, we present ENERGYVID, a universal spatio-temporal Energy-guided Video Diffusion model designed for zero-shot video synthesis and editing across diverse conditions. Specifically, we leverage off-the-shelf pre-trained networks to construct generic energy functions, guiding the generation process under specific conditions without the need for retraining. To precisely capture temporal dynamics related to motion conditions (e.g., pose sequences), we introduce a novel kernel Maximum Mean Discrepancy (MMD)-based energy function, which minimizes the global distribution discrepancy between the conditioning input and the generated video. Our extensive qualitative and quantitative experiments demonstrate that our algorithm consistently produces high-quality results across a wide range of motion and non-motion conditions, including text, face ID, style, poses, depths, sketches, canny edges, and segmentation maps, in the context of zero-shot video synthesis and editing. We will release source code upon acceptance of the paper.