Chengzu Li

29 papers A* 5Journal 20Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Confidence Estimation for LLMs in Multi-turn Interactions.
CoRR
Caiqi Zhang, Ruihan Yang, Xiaochen Zhu, Chengzu Li, Tiancheng Hu, Yijiang River Dong, Deqing Yang, Nigel Collier
2026 J jnl
How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing.
CoRR
Huanyu Zhang, Xuehai Bai, Chengzu Li, Chen Liang, Haochen Tian, Haodong Li, Ruichuan An, Yifan Zhang, Anna Korhonen, Zhang Zhang, Liang Wang, Tieniu Tan
2026 J jnl
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning.
CoRR
Chengzu Li, Zanyi Wang, Jiaang Li, Yi Xu, Han Zhou, Huanyu Zhang, Ruichuan An, Dengyang Jiang, Zhaochong An, Ivan Vulic, Serge J. Belongie, Anna Korhonen
2026 J jnl
Video Understanding: From Geometry and Semantics to Unified Models.
CoRR
Zhaochong An, Zirui Li, Mingqiao Ye, Feng Qiao, Jiaang Li, Zongwei Wu, Vishal Thengane, Chengzu Li, Lei Li, Luc Van Gool, Guolei Sun, Serge J. Belongie
2025 J jnl
11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis.
CoRR
Chengzu Li, Wenshan Wu, Huanyu Zhang, Qingtao Li, Zeyu Gao, Yan Xia, José Hernández-Orallo, Ivan Vulic, Furu Wei
2025 J jnl
A Call for New Recipes to Enhance Spatial Reasoning in MLLMs.
CoRR
Huanyu Zhang, Chengzu Li, Wenshan Wu, Shaoguang Mao, Yan Xia, Ivan Vulic, Zhang Zhang, Liang Wang, Tieniu Tan, Furu Wei
2025 J jnl
Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models.
CoRR
Ej Zhou, Caiqi Zhang, Tiancheng Hu, Chengzu Li, Nigel Collier, Ivan Vulic, Anna Korhonen
2025 J jnl
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation.
CoRR
Zanyi Wang, Dengyang Jiang, Liuzhuozheng Li, Sizhe Dang, Chengzu Li, Harry Yang, Guang Dai, Mengmeng Wang, Jingdong Wang
2025 — conf
Enriching Patent Claim Generation with European Patent Dataset.
EMNLP (Findings)
Lekang Jiang, Chengzu Li, Stefan Goetz
2025 J jnl
Enriching Patent Claim Generation with European Patent Dataset.
CoRR
Lekang Jiang, Chengzu Li, Stephan Goetz
2025 A* conf
Imagine While Reasoning in Space: Multimodal Visualization-of-Thought.
ICML
Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia, Shaoguang Mao, Li Dong, Ivan Vulic, Furu Wei
2025 J jnl
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought.
CoRR
Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia, Shaoguang Mao, Li Dong, Ivan Vulic, Furu Wei
2025 — conf
Large Language Models are Miscalibrated In-Context Learners.
ACL (Findings)
Chengzu Li, Han Zhou, Goran Glavas, Anna Korhonen, Ivan Vulic
2025 J jnl
Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs.
CoRR
Huanyu Zhang, Wenshan Wu, Chengzu Li, Ning Shang, Yan Xia, Yangyu Huang, Yifan Zhang, Li Dong, Zhang Zhang, Liang Wang, Tieniu Tan, Furu Wei
2025 — conf
Lost in Embeddings: Information Loss in Vision-Language Models.
EMNLP (Findings)
Wenyan Li, Raphael Tang, Chengzu Li, Caiqi Zhang, Ivan Vulic, Anders Søgaard
2025 J jnl
Lost in Embeddings: Information Loss in Vision-Language Models.
CoRR
Wenyan Li, Raphael Tang, Chengzu Li, Caiqi Zhang, Ivan Vulic, Anders Søgaard
2025 J jnl
Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation.
CoRR
Caiqi Zhang, Xiaochen Zhu, Chengzu Li, Nigel Collier, Andreas Vlachos
2025 J jnl
Visual Planning: Let's Think Only with Images.
CoRR
Yi Xu, Chengzu Li, Han Zhou, Xingchen Wan, Caiqi Zhang, Anna Korhonen, Ivan Vulic
2024 — conf
Semantic Map-based Generation of Navigation Instructions.
LREC/COLING
Chengzu Li, Chao Zhang, Simone Teufel, Rama Sanand Doddipatla, Svetlana Stoyanchev
2024 J jnl
Semantic Map-based Generation of Navigation Instructions.
CoRR
Chengzu Li, Chao Zhang, Simone Teufel, Rama Sanand Doddipatla, Svetlana Stoyanchev
2024 A* conf
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners.
EMNLP
Chengzu Li, Caiqi Zhang, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulic
2024 J jnl
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners.
CoRR
Chengzu Li, Caiqi Zhang, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulic
2023 A* conf
Binding Language Models in Symbolic Languages.
ICLR
Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu
2023 A* conf
Generating Data for Symbolic Language with Large Language Models.
EMNLP
Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu
2023 J jnl
Generating Data for Symbolic Language with Large Language Models.
CoRR
Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu
2023 J jnl
On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning.
CoRR
Chengzu Li, Han Zhou, Goran Glavas, Anna Korhonen, Ivan Vulic
2022 J jnl
Binding Language Models in Symbolic Languages.
CoRR
Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu
2022 A* conf
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models.
EMNLP
Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu
2022 J jnl
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models.
CoRR
Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir R. Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu