Xuehai He

5

Papers

86

Total Citations

Papers (5)

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

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

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning