| Learning Compact Vision Tokens for Efficient Large Multimodal Models | Jun 8, 2025 | Multimodal ReasoningToken Reduction | CodeCode Available | 1 |
| Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration | Jun 6, 2025 | Depth Estimationobject-detection | —Unverified | 0 |
| Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings | Jun 5, 2025 | RetrievalToken Reduction | —Unverified | 0 |
| Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers | Jun 5, 2025 | GPUText-to-Video Generation | —Unverified | 0 |
| SiLVR: A Simple Language-based Video Reasoning Framework | May 30, 2025 | MathMME | CodeCode Available | 1 |
| One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory | May 29, 2025 | Contrastive LearningText Retrieval | CodeCode Available | 2 |
| VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models | May 28, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models | May 26, 2025 | Token Reduction | CodeCode Available | 1 |
| The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training | May 25, 2025 | Reinforcement Learning (RL)Token Reduction | —Unverified | 0 |
| Not All Tokens Are What You Need In Thinking | May 23, 2025 | AllToken Reduction | CodeCode Available | 0 |
