Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights Paper • 2512.01816 • Published 7 days ago • 88
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Paper • 2504.00999 • Published Apr 1 • 95
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning Paper • 2410.06373 • Published Oct 8, 2024 • 36