4.8k citations
- Peking UniversityCN49 papers
- Tsinghua UniversityCN49 papers
- University of Science and Technology of ChinaCN41 papers
- Microsoft (United States)US29 papers
- Hong Kong University of Science and TechnologyHK24 papers
- Shanghai Jiao Tong UniversityCN20 papers
- Microsoft Research (United Kingdom)GB19 papers
- Zhejiang UniversityCN19 papers
- Chinese Academy of SciencesCN18 papers
- Fudan UniversityCN18 papers
- Beihang UniversityCN16 papers
- Carnegie Mellon UniversityUS13 papers
331 papers
Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning
Fanhong Li, Shurui Zheng, Zi Yin +3
Video foundation models now reach human-level accuracy on physical-reasoning benchmarks, yet such tasks require predicting unobserved physical outcomes. Do these models perform hum…
Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
Feier Qin, Xiao Li, Yi Zheng +5
Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to suppo…
CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
Yingrui Wu, Youkang Kong, Mingyang Zhao +3
Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic…
SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields
Youkang Kong, Yang Liu, Yue Dong +2
3D shapes from scanning, reconstruction, or AI-generated content often lack simple quad mesh layouts -- critical for efficient editing and modeling. Existing quad-remeshing techniq…
CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation
Yunfan Yang, Cuiling Lan, Jitao Sang +1
Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitiz…
From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning Engagement
Zixin Chen, Haotian Li, Zhe Liu +2
Large Language Models (LLMs) are increasingly used as learning companions, providing scaffolded explanations, hints, or step-by-step guidance. However, in current LLM-based learnin…