Chun-Kai Fan

WoW: Scaling Embodied Omni-World Model For Generalizable Manipulation Simulation

Robobench: A Comprehensive Evaluation Benchmark For Multimodal Large Language Models as Embodied Brain

SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents

EVA: An Embodied World Model for Future Video Anticipation

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Empowering World Models with Reflection for Embodied Video Prediction

SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning

SparseVLM: Visual Token Sparsification for Efficient Vision Language Models Inference

Discovering Long-Term Effects on Parameter Efficient Fine-tuning