ArmenJeddi / saint
a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity
☆11Updated this week
Alternatives and similar repositories for saint:
Users that are interested in saint are comparing it to the libraries listed below
- [ACL 2023] PuMer: Pruning and Merging Tokens for Efficient Vision Language Models☆29Updated 6 months ago
- [CVPR '25] Official implementation of the paper "Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages", accepted at (an…☆9Updated this week
- A benchmark dataset and simple code examples for measuring the perception and reasoning of multi-sensor Vision Language models.☆18Updated 3 months ago
- The official implementation for MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning (CVPR '24)☆44Updated 3 weeks ago
- Implementation of the model "Hedgehog" from the paper: "The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry"☆13Updated last year
- Adapting LLaMA Decoder to Vision Transformer☆28Updated 10 months ago
- PyTorch code for "ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning"☆19Updated 5 months ago
- Collect papers about Mamba (a selective state space model).☆14Updated 7 months ago
- Implementation of the model: "(MC-ViT)" from the paper: "Memory Consolidation Enables Long-Context Video Understanding"☆21Updated 2 months ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆19Updated 7 months ago
- Pytorch Implementation for CVPR 2024 paper: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation☆36Updated last month
- CLIP-MoE: Mixture of Experts for CLIP☆29Updated 5 months ago
- Implementation of the "the first large-scale multimodal mixture of experts models." from the paper: "Multimodal Contrastive Learning with…☆27Updated 2 months ago
- [CVPR2025] Breaking the Low-Rank Dilemma of Linear Attention☆12Updated 3 weeks ago
- Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning☆16Updated last week
- The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".☆13Updated last week
- [NeurIPS 2024] official code release for our paper "Revisiting the Integration of Convolution and Attention for Vision Backbone".☆35Updated 2 months ago
- [NeurIPS 2024] TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration☆23Updated 5 months ago
- ☆40Updated 4 months ago
- The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". …☆51Updated 4 months ago
- ☆22Updated 11 months ago
- This is the official repo for ByteVideoLLM/Dynamic-VLM☆20Updated 3 months ago
- The official code for MedAgent_Pro☆13Updated this week
- GIFT: Generative Interpretable Fine-Tuning☆20Updated 5 months ago
- More dimensions = More fun☆21Updated 8 months ago
- [ECCV 2024] Soft Prompt Generation for Domain Generalization☆19Updated 6 months ago
- [ECCV 2024 Oral] Official implementation of the paper "DEVIAS: Learning Disentangled Video Representations of Action and Scene"☆18Updated 5 months ago
- Official implementation of NeurIPS 2024 "Visual Fourier Prompt Tuning"☆26Updated 2 months ago
- [EMNLP 2024] Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality☆16Updated 5 months ago
- Official implementation of Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More☆17Updated last month