Zedong Wang (Jacky)
ZedongWangAI
AI & ML interests
Computer Vision, Multi-task Learning, Multi-modal Learning, Optimizers in the era of (M)LLMs.
Recent Activity
upvoted
a
paper
13 days ago
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery
Simulation
upvoted
a
paper
14 days ago
Token-Shuffle: Towards High-Resolution Image Generation with
Autoregressive Models
Organizations
Collections
2
-
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 34 -
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 89 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 53 -
MoCha: Towards Movie-Grade Talking Character Synthesis
Paper • 2503.23307 • Published • 133
models
0
None public yet
datasets
0
None public yet