Kun Xiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kun Xiang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Hanhui Li
Shenzhen Campus of Sun Yat-sen University, Shenzhen, China
3 shared publications - Terry Jingchen Zhang
ETH Zurich, Zurich, Switzerland
3 shared publications - Xiaodan Liang
Shenzhen Campus of Sun Yat-sen University
3 shared publications Jianhua Han
Yinwang Intelligent Technology Co., Ltd., Shenzhen, China
2 shared publications- Bin Dong
School of Mathematical Sciences Peking University 100871 Beijing P.R. CHINA
1 shared publication - Bingqian Lin
Shanghai Jiao Tong University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11662-11670
Fetch, Frame, and Focus: Retrieval-Augmented Panoramic-Spotlight Memory for Scalable Vector Graphics Generation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11662-11670
Open AccessFetch, Frame, and Focus: Retrieval-Augmented Panoramic-Spotlight Memory for Scalable Vector Graphics Generation
- 12 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-22
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
The convergence of embodied intelligence and world models has catalyzed growing interest in integrating physical laws into AI systems. While prior surveys have examined world models and embodied intelligence separately, we focus on the progression that connects these capabilities as a unified developmental pathway from passive observation to active physical comprehension. This survey provides a systematic framework revealing how physical AI advances through four interconnected stages: perception transforms sensory data into structured physical representations, reasoning derives explanations from observed phenomena, modeling enables predictive simulation grounded in physical principles, and embodied interaction closes the loop through physical manipulation and environmental feedback. Each stage enables and enhances the next: perceptual grounding supports causal reasoning, reasoning unlocks predictive capabilities, and robust models drive genuine physical interaction. Through analysis of developments spanning architectural innovations, training methodologies, causal inference, and embodied systems, we synthesize how physical understanding emerges through cumulative integration across this progression. Our framework reveals the evolution from isolated, task-specific solutions toward integrated architectures that advance from pattern recognition toward causal reasoning and counterfactual prediction. This perspective provides foundations for next-generation physical AI systems with direct implications for safe, generalizable, and interpretable deployment across robotics, scientific discovery, and autonomous systems. We maintain a continuously updated taxonomy repository at https://github.com/AI4Phys/Awesome-AI-for-Physics.
- 12 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-22
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
The convergence of embodied intelligence and world models has catalyzed growing interest in integrating physical laws into AI systems. While prior surveys have examined world models and embodied intelligence separately, we focus on the progression that connects these capabilities as a unified developmental pathway from passive observation to active physical comprehension. This survey provides a systematic framework revealing how physical AI advances through four interconnected stages: perception transforms sensory data into structured physical representations, reasoning derives explanations from observed phenomena, modeling enables predictive simulation grounded in physical principles, and embodied interaction closes the loop through physical manipulation and environmental feedback. Each stage enables and enhances the next: perceptual grounding supports causal reasoning, reasoning unlocks predictive capabilities, and robust models drive genuine physical interaction. Through analysis of developments spanning architectural innovations, training methodologies, causal inference, and embodied systems, we synthesize how physical understanding emerges through cumulative integration across this progression. Our framework reveals the evolution from isolated, task-specific solutions toward integrated architectures that advance from pattern recognition toward causal reasoning and counterfactual prediction. This perspective provides foundations for next-generation physical AI systems with direct implications for safe, generalizable, and interpretable deployment across robotics, scientific discovery, and autonomous systems. We maintain a continuously updated taxonomy repository at https://github.com/AI4Phys/Awesome-AI-for-Physics.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5725-5741
AtomThink: Multimodal Slow Thinking With Atomic Step Reasoning
In this paper, we address the challenging task of multimodal reasoning by incorporating the notion of “slow thinking” into multimodal large language models (MLLMs). Our core idea is that models can learn to adaptively use different levels of reasoning to tackle questions of varying complexity. We propose a novel paradigm of Self-structured Chain of Thought (SCoT), which consists of minimal semantic atomic steps. Unlike existing methods that rely on structured templates or free-form paradigms, our method not only generates flexible CoT structures for various complex tasks but also mitigates the phenomenon of overthinking for easier tasks. To introduce structured reasoning into visual cognition, we design a novel AtomThink framework with four key modules: (i) a data engine to generate high-quality multimodal reasoning paths; (ii) a supervised fine-tuning (SFT) process with serialized inference data; (iii) a policy-guided multi-turn inference method; and (iv) an atomic capability metric to evaluate the single-step utilization rate. Extensive experiments demonstrate that the proposed AtomThink significantly improves the performance of baseline MLLMs, achieving more than 10% average accuracy gains on MathVista and MathVerse. Compared to state-of-the-art structured CoT approaches, our method not only achieves higher accuracy but also improves data utilization by 5 × and boosts inference efficiency by 85.3%.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (5) , 5725-5741
AtomThink: Multimodal Slow Thinking With Atomic Step Reasoning
In this paper, we address the challenging task of multimodal reasoning by incorporating the notion of “slow thinking” into multimodal large language models (MLLMs). Our core idea is that models can learn to adaptively use different levels of reasoning to tackle questions of varying complexity. We propose a novel paradigm of Self-structured Chain of Thought (SCoT), which consists of minimal semantic atomic steps. Unlike existing methods that rely on structured templates or free-form paradigms, our method not only generates flexible CoT structures for various complex tasks but also mitigates the phenomenon of overthinking for easier tasks. To introduce structured reasoning into visual cognition, we design a novel AtomThink framework with four key modules: (i) a data engine to generate high-quality multimodal reasoning paths; (ii) a supervised fine-tuning (SFT) process with serialized inference data; (iii) a policy-guided multi-turn inference method; and (iv) an atomic capability metric to evaluate the single-step utilization rate. Extensive experiments demonstrate that the proposed AtomThink significantly improves the performance of baseline MLLMs, achieving more than 10% average accuracy gains on MathVista and MathVerse. Compared to state-of-the-art structured CoT approaches, our method not only achieves higher accuracy but also improves data utilization by 5 × and boosts inference efficiency by 85.3%.