Xin Eric Wang

Constructing a 3D Scene from a Single Image

$PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

SAFER: Risk-Constrained Sample-then-Filter in Large Language Models

Cite-While-You-Generate: Training-Free Evidence Attribution for Multimodal Clinical Summarization

Self-Resource Allocation in Multi-Agent LLM Systems

The Unreasonable Effectiveness of Scaling Agents for Computer Use

CCC: Prompt Evolution for Video Generation via Structured MLLM Feedback

HexMachina: Self-Evolving Multi-Agent System for Continual Learning of Catan

GRIT: Teaching MLLMs to Think with Images

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

Multimodal Situational Safety

Agent S: An Open Agentic Framework that Uses Computers Like a Human

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos

Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA

VIA: Unified Spatiotemporal Video Adaptation for Global and Local Video Editing