[EMNLP 2025 main π₯] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"
β107Oct 12, 2025Updated 4 months ago
Alternatives and similar repositories for DART
Users that are interested in DART are comparing it to the libraries listed below
Sorting:
- (NeurIPS 2025 π₯) Official implementation for "Efficient Multi-modal Large Language Models via Progressive Consistency Distillation"β41Feb 11, 2026Updated 2 weeks ago
- π Collection of token-level model compression resources.β190Sep 3, 2025Updated 5 months ago
- Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"β24Mar 4, 2025Updated 11 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductionβ141Mar 6, 2025Updated 11 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Modelβ37Jan 8, 2025Updated last year
- [AAAI 2025]This repo contains evaluation code for the paper βUrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models inβ¦β36Apr 10, 2025Updated 10 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Modelsβ164Sep 27, 2025Updated 5 months ago
- [ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMsβ82Jan 17, 2026Updated last month
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"β55Oct 9, 2025Updated 4 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.β106Jun 29, 2025Updated 8 months ago
- Code release for VTW (AAAI 2025 Oral)β64Nov 4, 2025Updated 3 months ago
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videosβ115Dec 12, 2025Updated 2 months ago
- A paper list of some recent works about Token Compress for Vit and VLMβ835Updated this week
- (ICLR 2026 π₯) Code for "The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs"β74Feb 9, 2026Updated 2 weeks ago
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMsβ68Jul 1, 2025Updated 8 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.β87Sep 20, 2025Updated 5 months ago
- A Framework for Collaboration of Experts from Benchmarkβ13Apr 27, 2025Updated 10 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.β86Oct 26, 2025Updated 4 months ago
- Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.β45Oct 29, 2025Updated 4 months ago
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Modelsβ56Jan 30, 2026Updated last month
- π Awesome papers on token redundancy reductionβ11Mar 12, 2025Updated 11 months ago
- β10Oct 20, 2023Updated 2 years ago
- Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation (CVPR24)β11Jun 16, 2024Updated last year
- β14Apr 25, 2025Updated 10 months ago
- Collection of papers about video-audio understandingβ22Dec 26, 2025Updated 2 months ago
- Code for paper: Unraveling the Shift of Visual Information Flow in MLLMs: From Phased Interaction to Efficient Inferenceβ13Jun 7, 2025Updated 8 months ago
- [CVPR2024 highlight] Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching (G-VBSM)β28Oct 9, 2024Updated last year
- [CVPR2025] Code Release of Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perceptionβ20Jun 17, 2025Updated 8 months ago
- Towards Efficient Multimodal Large Language Models: A Survey on Token Compressionβ112Jan 13, 2026Updated last month
- β16Mar 24, 2025Updated 11 months ago
- β17Jun 14, 2024Updated last year
- η΅εη§ζ倧ε¦ζ¬η§θ―Ύη¨δ»£η γβ16Dec 31, 2023Updated 2 years ago
- [ICLR'25] Streaming Video Question-Answering with In-context Video KV-Cache Retrievalβ104Nov 4, 2025Updated 3 months ago
- [CVPR 2026] Accelerating Streaming Video Large Language Models via Hierarchical Token Compressionβ44Updated this week
- The code of the paper "Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation" (CVPR2023)β40Mar 25, 2023Updated 2 years ago
- γIEEE TITS2025γUnity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identificationβ24Dec 30, 2024Updated last year
- [EMNLP 2025 Main] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruningβ34Jan 11, 2026Updated last month
- [NeurIPS 2025] VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulationβ67Sep 20, 2025Updated 5 months ago
- [NeurIPS 2025 π₯] FakeVLM: Advancing Synthetic Image Detection through Explainable Multimodal Models and Fine-Grained Artifact Analysisβ120Sep 24, 2025Updated 5 months ago