Mengyu Wang

Associate Professor@Harvard University·美国·OpenReview

研究方向

Semi-Supervised Learning · Vision-Language Models · Large Language Models · Generative Models · World Models · Robotics · Vision-Language Action Models · Fairness

6.0

PAGE-4D: Disentangled Pose and Geometry Estimation for VGGT-4D Perception

ICLR 2026Poster

通讯

5.5

Uncertainty quantification in clinical settings: A retinal fundus screening study and benchmarking

ICLR 2026Rejected

4.0

Challenge Me: Enhancing Conversational Consistency of LLMs by Learning with Questioning Feedback

合作者 (20)

Mengyu Wang

PAGE-4D: Disentangled Pose and Geometry Estimation for VGGT-4D Perception

Uncertainty quantification in clinical settings: A retinal fundus screening study and benchmarking

SeqRL: Sequence-Attentive Reinforcement Learning for LLM Jailbreaking

SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing

Impact of Data Distribution on Fairness Guarantees in Equitable Deep Learning

FairFedMed: Achieving Equity in Medical Federated Learning via FairLoRA

Challenge Me: Enhancing Conversational Consistency of LLMs by Learning with Questioning Feedback