38 citations · 52 across the 24 of their papers we have counts for
25 papers
GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
Weixian Waylon Li, Jiaxin Zhang, Han Zhou +4
Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipel…
Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
Jiaang Li, Chengzu Li, Zhaochong An +4
Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. However, they often fail on vis…
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
Chao Chen, Chengzu Li, Zhiwei Li +2
Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesigned environments between stages, requiring practitioners to heuristically inf…
When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs
Zhichao Yang, Caiqi Zhang, Ruihan Yang +3
Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language models using global…
Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
Jiusong Ge, Yingkang Zhan, Wenjie Zhao +13
Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level features at high magnification and…
Video Understanding: From Geometry and Semantics to Unified Models
Zhaochong An, Zirui Li, Mingqiao Ye +9
Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently…
How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
Huanyu Zhang, Xuehai Bai, Chengzu Li +9
Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In contrast, human communication i…
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
Chengzu Li, Zanyi Wang, Jiaang Li +9
Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the d…
Confidence Estimation for LLMs in Multi-turn Interactions
Caiqi Zhang, Ruihan Yang, Xiaochen Zhu +5
While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings.…
Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
Huanyu Zhang, Wenshan Wu, Chengzu Li +9
While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how…
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
Zanyi Wang, Dengyang Jiang, Liuzhuozheng Li +6
Referring Video Object Segmentation (RVOS) requires segmenting specific objects in a video guided by a natural language description. The core challenge of RVOS is to anchor abstrac…
Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models
Ej Zhou, Caiqi Zhang, Tiancheng Hu +4
Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large Language Models (LLMs). However, t…
Lost in Embeddings: Information Loss in Vision-Language Models
Wenyan Li, Raphael Tang, Chengzu Li +3
Vision--language models (VLMs) often process visual inputs through a pretrained vision encoder, followed by a projection into the language model's embedding space via a connector c…
11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis
Chengzu Li, Wenshan Wu, Huanyu Zhang +6
For human cognitive process, spatial reasoning and perception are closely entangled, yet the nature of this interplay remains underexplored in the evaluation of multimodal large la…
Enriching Patent Claim Generation with European Patent Dataset
Lekang Jiang, Chengzu Li, Stephan Goetz
Drafting patent claims is time-intensive, costly, and requires professional skill. Therefore, researchers have investigated large language models (LLMs) to assist inventors in writ…
LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
Caiqi Zhang, Xiaochen Zhu, Chengzu Li +2
Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence es…
Visual Planning: Let's Think Only with Images
Yi Xu, Chengzu Li, Han Zhou +4
Recent advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have substantially enhanced machine reasoning across diverse tasks. However, these model…
Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes
Huanyu Zhang, Chengzu Li, Wenshan Wu +8
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks. However, recent studies have exposed critical limitations in the…
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
Chengzu Li, Wenshan Wu, Huanyu Zhang +5
Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it s…
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
Chengzu Li, Caiqi Zhang, Han Zhou +3
Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `no…
Semantic Map-based Generation of Navigation Instructions
Chengzu Li, Chao Zhang, Simone Teufel +2
We are interested in the generation of navigation instructions, either in their own right or as training material for robotic navigation task. In this paper, we propose a new appro…
Large Language Models are Miscalibrated In-Context Learners
Chengzu Li, Han Zhou, Goran Glavaš +2
When adapting ICL with or without fine-tuning, we are curious about whether the instruction-tuned language model is able to achieve well-calibrated results without suffering from t…
Generating Data for Symbolic Language with Large Language Models
Jiacheng Ye, Chengzu Li, Lingpeng Kong +1
While large language models (LLMs) bring not only performance but also complexity, recent work has started to turn LLMs into data generators rather than task inferencers, where ano…
Binding Language Models in Symbolic Languages
Zhoujun Cheng, Tianbao Xie, Peng Shi +9
Though end-to-end neural approaches have recently been dominating NLP tasks in both performance and ease-of-use, they lack interpretability and robustness. We propose Binder, a tra…