NUS-HPC-AI-Lab / R-MeeToLinks
Give us minutes, we give back a faster Mamba. The official implementation of "Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training".
☆40Updated 11 months ago
Alternatives and similar repositories for R-MeeTo
Users that are interested in R-MeeTo are comparing it to the libraries listed below
Sorting:
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆51Updated 11 months ago
- ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching☆104Updated last year
- Data distillation benchmark☆71Updated 5 months ago
- [CVPR2024] Efficient Dataset Distillation via Minimax Diffusion☆102Updated last year
- This repository organizes the Imagnet1k dataset into 10 coarse classes, where each class consists of semantically similar image categorie…☆22Updated last year
- [ICCV2023] Dataset Quantization☆261Updated last year
- ☆36Updated 6 months ago
- [CVPR2024 highlight] Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching (G-VBSM)☆28Updated last year
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆90Updated 2 weeks ago
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆132Updated last year
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆200Updated 6 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆75Updated last month
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆156Updated 2 months ago
- [NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".☆188Updated 2 years ago
- [NeurIPS'25] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆60Updated last month
- Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023☆93Updated last year
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆112Updated 4 months ago
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆104Updated 2 years ago
- (NeurIPS 2023 spotlight) Large-scale Dataset Distillation/Condensation, 50 IPC (Images Per Class) achieves the highest 60.8% on original …☆132Updated last year
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆339Updated last year
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆67Updated last week
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆49Updated last year
- [ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators☆46Updated last year
- Elucidated Dataset Condensation (NeurIPS 2024)☆20Updated last year
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆107Updated 2 months ago
- The official implementation of 《MLLMs-Augmented Visual-Language Representation Learning》☆31Updated last year
- [ICLR'25] Reconstructive Visual Instruction Tuning☆128Updated 7 months ago
- A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"☆46Updated last year
- [CVPR 2024] On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm☆78Updated 9 months ago
- CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for task-aware parameter-efficient fine-tuning(NeurIPS 2024)☆53Updated 10 months ago