Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper
• 2410.06373 • Published
• 36
Representation Learning & Generation
-
-
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 95 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 54 -
MoCha: Towards Movie-Grade Talking Character Synthesis
Paper • 2503.23307 • Published • 139 -
Z1: Efficient Test-time Scaling with Code
Paper • 2504.00810 • Published • 26 -
Scaling Language-Free Visual Representation Learning
Paper • 2504.01017 • Published • 32 -
Multi-Token Attention
Paper • 2504.00927 • Published • 56 -
Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
Paper • 2504.00557 • Published • 15