| EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation | May 16, 2025 | DiversityRAG | —Unverified | 0 |
| Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method | May 12, 2025 | Semantic CompressionSemantic Similarity | —Unverified | 0 |
| ZipR1: Reinforcing Token Sparsity in MLLMs | Apr 23, 2025 | Token Reduction | —Unverified | 0 |
| DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs | Apr 23, 2025 | Token ReductionVideo Understanding | —Unverified | 0 |
| Dynamic Compressing Prompts for Efficient Inference of Large Language Models | Apr 15, 2025 | Token Reduction | CodeCode Available | 0 |
| Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features | Apr 1, 2025 | Token Reduction | —Unverified | 0 |
| Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning | Mar 31, 2025 | Semantic SegmentationToken Reduction | —Unverified | 0 |
| Faster Parameter-Efficient Tuning with Token Redundancy Reduction | Mar 26, 2025 | Token Reduction | CodeCode Available | 0 |
| Token Dynamics: Towards Efficient and Dynamic Video Token Representation for Video Large Language Models | Mar 21, 2025 | Computational EfficiencyToken Reduction | —Unverified | 0 |
| Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers | Mar 14, 2025 | GPUMamba | —Unverified | 0 |
