vision tasks
- Accurate and Efficient Low-Rank Model Merging in Core Space
- Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
- Improving Bilinear RNN with Closed-loop Control
- Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
- Pay Attention to Small Weights
- Stepsize anything: A unified learning rate schedule for budgeted-iteration training
- Understanding and Enhancing Mask-Based Pretraining towards Universal Representations