UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation Paper • 2506.03147 • Published 30 days ago • 58
Taming LLMs by Scaling Learning Rates with Gradient Grouping Paper • 2506.01049 • Published Jun 1 • 36
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Paper • 2504.00999 • Published Apr 1 • 93
WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes Paper • 2503.13435 • Published Mar 17 • 17
Switch EMA: A Free Lunch for Better Flatness and Sharpness Paper • 2402.09240 • Published Feb 14, 2024 • 3
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning Paper • 2410.06373 • Published Oct 8, 2024 • 34