Weidi Xie

Associate Professor@Shanghai Jiaotong University·中国·OpenReview

研究方向

Computer vision · Representation Learning · Video Understanding · Computer Vision · Deep Learning · computer vision · deep learning · machine learning.

6.5

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

ICLR 2026Poster

通讯

4.0

Inferring Dynamic Physical Properties from Video Foundation Models

ICLR 2026Withdrawn

三作

7.3

Universal Video Temporal Grounding with Generative Multi-modal Large Language Models

NeurIPS 2025Poster

通讯

6.7

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

ICLR 2025Poster

4.6

Unlocking Video-LLM via Agent-of-Thoughts Distillation

合作者 (20)

Weidi Xie

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Inferring Dynamic Physical Properties from Video Foundation Models

Universal Video Temporal Grounding with Generative Multi-modal Large Language Models

EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos

A Sanity Check for AI-generated Image Detection

Track-On: Transformer-based Online Point Tracking with Memory

Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

Unlocking Video-LLM via Agent-of-Thoughts Distillation