Juncheng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Juncheng Li has a total of 99 co-authors. Here are the top co-authors by number of shared publications:
- Siliang Tang
Zhejiang University, Hangzhou, Zhejiang, China
15 shared publications - Yueting Zhuang
Zhejiang University, China
14 shared publications - Wenqiao Zhang
Zhejiang University, Hangzhou, China
9 shared publications - Wei Ji
Nanjing University, Suzhou, China
7 shared publications - Hao Fei
National University of Singapore, Singapore, Singapore
6 shared publications - Jun Xiao
Zhejiang University, Hangzhou, Zhejiang, China
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5077-5085
INTACT: Intent-Centered Self-Improvement for Vision-Language Navigation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5077-5085
Open AccessINTACT: Intent-Centered Self-Improvement for Vision-Language Navigation
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 65-74
OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 65-74
Open AccessOmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 18050-18052
The 1st International Workshop on Joint Audio-Video Comprehension and Generation (JAV-CG)
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 18050-18052
Open AccessThe 1st International Workshop on Joint Audio-Video Comprehension and Generation (JAV-CG)
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 857-868
Generation-Augmented Video Corpus Moment Retrieval
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 857-868
Open AccessGeneration-Augmented Video Corpus Moment Retrieval
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4137-4148
Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4137-4148
Open AccessTowards Meta-Cognitive Knowledge Editing for Multimodal LLMs
- Top Cited Papers
- 19 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 320
MAKIMA: Tuning-free multi-attribute open-domain video editing via mask-guided attention modulation
- 19 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 320
Top Cited PapersMAKIMA: Tuning-free multi-attribute open-domain video editing via mask-guided attention modulation
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (6) , 6208-6224
Momentor++: Advancing Video Large Language Models With Fine-Grained Long Video Reasoning
Large Language Models (LLMs) exhibit remarkable proficiency in understanding and managing text-based tasks.Many works try to transfer these capabilities to the video domain, which are referred to as Video-LLMs. However, current Video-LLMs can only grasp the coarse-grained semantics and are unable to efficiently handle tasks involving the comprehension or localization of specific video segments. To address these challenges, we propose Momentor, a Video-LLM designed to perform fine-grained temporal understanding tasks. To facilitate the training of Momentor, we develop an automatic data generation engine to build Moment-10M, a large-scale video instruction dataset with segment-level instruction data. Building upon the foundation of the previously published Momentor and the Moment-10M dataset, we further extend this work by introducing a Spatio-Temporal Token Consolidation (STTC) method, which can merge redundant visual tokens spatio-temporally in a parameter-free manner, thereby significantly promoting computational efficiency while preserving fine-grained visual details. We integrate STTC with Momentor to develop Momentor++ and validate its performance on various benchmarks. Momentor demonstrates robust capabilities in fine-grained temporal understanding and localization. Further, Momentor++ excels in efficiently processing and analyzing extended videos with complex events, showcasing marked advancements in handling extensive temporal contexts.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (6) , 6208-6224
Momentor++: Advancing Video Large Language Models With Fine-Grained Long Video Reasoning
Large Language Models (LLMs) exhibit remarkable proficiency in understanding and managing text-based tasks.Many works try to transfer these capabilities to the video domain, which are referred to as Video-LLMs. However, current Video-LLMs can only grasp the coarse-grained semantics and are unable to efficiently handle tasks involving the comprehension or localization of specific video segments. To address these challenges, we propose Momentor, a Video-LLM designed to perform fine-grained temporal understanding tasks. To facilitate the training of Momentor, we develop an automatic data generation engine to build Moment-10M, a large-scale video instruction dataset with segment-level instruction data. Building upon the foundation of the previously published Momentor and the Moment-10M dataset, we further extend this work by introducing a Spatio-Temporal Token Consolidation (STTC) method, which can merge redundant visual tokens spatio-temporally in a parameter-free manner, thereby significantly promoting computational efficiency while preserving fine-grained visual details. We integrate STTC with Momentor to develop Momentor++ and validate its performance on various benchmarks. Momentor demonstrates robust capabilities in fine-grained temporal understanding and localization. Further, Momentor++ excels in efficiently processing and analyzing extended videos with complex events, showcasing marked advancements in handling extensive temporal contexts.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13297-13303
Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13297-13303
Open AccessChart-HQA: A Benchmark for Hypothetical Question Answering in Charts
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13273-13280
FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13273-13280
Open AccessFormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11648-11656
Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11648-11656
Open AccessEvaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks