PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation Paper • 2403.09192 • Published Mar 14, 2024
Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence Paper • 2407.18899 • Published Jul 26, 2024
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval Paper • 2409.01156 • Published Sep 2, 2024
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval Paper • 2506.08887 • Published Jun 10 • 4
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning Paper • 2507.01006 • Published Jul 1 • 238
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning Paper • 2507.01006 • Published Jul 1 • 238