THU-MIG / VTC-CLS
official repo for paper "[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs"
☆20Updated 2 weeks ago
Alternatives and similar repositories for VTC-CLS:
Users that are interested in VTC-CLS are comparing it to the libraries listed below
- [NeurIPS 2024] Official PyTorch implementation of "Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives"☆39Updated 5 months ago
- The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". …☆52Updated 6 months ago
- [CVPR2024 Highlight] Official implementation for Transferable Visual Prompting. The paper "Exploring the Transferability of Visual Prompt…☆39Updated 4 months ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆24Updated 2 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆28Updated 4 months ago
- Official Repository of Personalized Visual Instruct Tuning☆28Updated 2 months ago
- Official implementation of MC-LLaVA.☆26Updated 3 months ago
- ☆83Updated last month
- [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training☆40Updated last month
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆36Updated 2 months ago
- This repository houses the code for the paper - "The Neglected of VLMs"☆28Updated last week
- Rui Qian, Xin Yin, Dejing Dou†: Reasoning to Attend: Try to Understand How <SEG> Token Works (CVPR 2025)☆30Updated last week
- Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types☆18Updated 3 weeks ago
- [CVPR 2025] Few-shot Recognition via Stage-Wise Retrieval-Augmented Finetuning☆17Updated last month
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆32Updated 9 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆73Updated 11 months ago
- Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆26Updated last month
- CLIP-MoE: Mixture of Experts for CLIP☆32Updated 7 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆32Updated 3 weeks ago
- The official repository for paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".☆38Updated 2 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆58Updated 2 weeks ago
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆86Updated 9 months ago
- [NeurIPS 2024] Official PyTorch implementation of LoTLIP: Improving Language-Image Pre-training for Long Text Understanding☆43Updated 3 months ago
- ☆15Updated 2 months ago
- ☆44Updated last week
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆11Updated 2 months ago
- Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"☆25Updated last month
- LEO: A powerful Hybrid Multimodal LLM☆17Updated 3 months ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆39Updated 2 months ago
- [ECCV 2024] ControlCap: Controllable Region-level Captioning☆74Updated 6 months ago