model generalizability
- AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining
- Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
- Enhancing Contrastive Learning with Variable Similarity
- Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation