Dit-Yan Yeung

10

Papers

176

Total Citations

1

Affiliations

Affiliations

Hong Kong University of Science and Technology

Papers (10)

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception

Implicit Concept Removal of Diffusion Models

Learning 3D Persistent Embodied World Models

Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection

RoboDreamer: Learning Compositional World Models for Robot Imagination

G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o

Gaussian Shell Maps for Efficient 3D Human Generation