EvelynZhang-epiclab / SiToLinks
[AAAI-2025] The offical code for SiTo （Similarity-based Token Pruning for Stable Diffusion Models）
☆40Updated 6 months ago
Alternatives and similar repositories for SiTo
Users that are interested in SiTo are comparing it to the libraries listed below
Sorting:
- [ICCV2025]Generate one 2K image on single 3090 GPU!☆79Updated 3 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" and "Sp…☆216Updated last week
- Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"☆81Updated 3 months ago
- [ICCV2025 highlight]Rectifying Magnitude Neglect in Linear Attention☆55Updated 5 months ago
- Official repository of InLine attention (NeurIPS 2024)☆57Updated last year
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆53Updated 3 months ago
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆96Updated 2 months ago
- [CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for…☆108Updated 3 months ago
- a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity☆40Updated 7 months ago
- [CVPR 2025] The official implementation of "CacheQuant: Comprehensively Accelerated Diffusion Models"☆33Updated last month
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆38Updated 9 months ago
- ☆14Updated 8 months ago
- [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think☆231Updated 2 months ago
- 📚 Collection of awesome generation acceleration resources.☆375Updated 5 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆100Updated 6 months ago
- [CVPR2025] FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression☆58Updated 2 months ago
- 📖 This is a repository for organizing papers, codes, and other resources related to unified multimodal models.☆339Updated 2 months ago
- 📚 Collection of token-level model compression resources.☆187Updated 3 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆82Updated 3 months ago
- Survey: https://arxiv.org/pdf/2507.20198☆257Updated last week
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆133Updated last year
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆93Updated 11 months ago
- Official repository of Polarity-aware Linear Attention for Vision Transformers (ICLR 2025)☆81Updated 2 months ago
- Implements VAR+CLIP for text-to-image (T2I) generation☆146Updated 11 months ago
- [NeurIPS'25] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆66Updated 2 months ago
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆108Updated 3 months ago
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆114Updated 5 months ago
- [CVPRW 2025] UniToken is an auto-regressive generation model that combines discrete and continuous representations to process visual inpu…☆97Updated 8 months ago
- [CVPR 2025 Highlight] TinyFusion: Diffusion Transformers Learned Shallow☆153Updated 3 weeks ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆135Updated 9 months ago