Cheng Han

Assistant Professor@University of Missouri-Kansas City·美国·OpenReview

研究方向

Indoor Navigation · AI Agent · Multimodal Learning · Vision Language Action · Diffusion Model · Representation Learning · Explainable AI · Efficient AI · Computer Vision · Image Classification

5.5

合作者 (20)

Cheng Han

TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching

Towards Long-Form Spatio-Temporal Video Grounding

Beyond Next-Token Prediction: Diffusion vs. Autoregressive Reasoning in LLMs

Probabilistic Token Alignment for Large Language Model Fusion

All You Need is One: Capsule Prompt Tuning with a Single Vector

Probabilistic Token Alignment for Large Language Model Fusion

Re-Imagining Multimodal Instruction Tuning: A Representation View