Zedong Wang's picture

5 42 1

Zedong Wang

JackyWangAI

·

https://jacky1128.github.io

AI & ML interests

Computer Vision, Multi-task Learning.

Recent Activity

upvoted a paper 8 days ago

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

upvoted a paper 18 days ago

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

upvoted a paper 18 days ago

Less is More: Recursive Reasoning with Tiny Networks

View all activity

Organizations

commented 2 papers 3 months ago

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

Paper • 2507.21049 • Published Jul 28 • 40 •

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

Paper • 2507.21049 • Published Jul 28 • 40 •

commented a paper 5 months ago

Taming LLMs by Scaling Learning Rates with Gradient Grouping

Paper • 2506.01049 • Published Jun 1 • 38 •

commented 4 papers 7 months ago

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Paper • 2504.00999 • Published Apr 1 • 93 •

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Paper • 2504.00999 • Published Apr 1 • 93 •

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Paper • 2504.00999 • Published Apr 1 • 93 •

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization

Paper • 2504.00999 • Published Apr 1 • 93 •

commented 3 papers about 1 year ago

Switch EMA: A Free Lunch for Better Flatness and Sharpness

Paper • 2402.09240 • Published Feb 14, 2024 • 4 •

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Paper • 2410.06373 • Published Oct 8, 2024 • 35 •

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Paper • 2410.06373 • Published Oct 8, 2024 • 35 •