| Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality | May 23, 2025 | In-Context LearningToken Reduction | CodeCode Available | 3 |
| CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms | May 22, 2025 | Token Reduction | CodeCode Available | 1 |
| Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning | May 22, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM | May 21, 2025 | DecoderToken Reduction | CodeCode Available | 1 |
| DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models | May 20, 2025 | GSM8KMathematical Reasoning | —Unverified | 0 |
| STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference | May 18, 2025 | Token Reduction | —Unverified | 0 |
| EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation | May 16, 2025 | DiversityRAG | —Unverified | 0 |
| Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration | May 16, 2025 | DenoisingToken Reduction | CodeCode Available | 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 |
