THU-MIG / VTC-CLSLinks
official repo for paper "[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs"
☆23Updated 8 months ago
Alternatives and similar repositories for VTC-CLS
Users that are interested in VTC-CLS are comparing it to the libraries listed below
Sorting:
- The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". …☆61Updated last year
- [CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"☆50Updated 6 months ago
- [CVPR2024 Highlight] Official implementation for Transferable Visual Prompting. The paper "Exploring the Transferability of Visual Prompt…☆46Updated last year
- CLIP-MoE: Mixture of Experts for CLIP☆51Updated last year
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆59Updated last year
- Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision☆42Updated 2 months ago
- VideoHallucer, The first comprehensive benchmark for hallucination detection in large video-language models (LVLMs)☆41Updated 2 weeks ago
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆41Updated 2 months ago
- Rui Qian, Xin Yin, Dejing Dou†: Reasoning to Attend: Try to Understand How <SEG> Token Works (CVPR 2025)☆51Updated 2 months ago
- [NeurIPS 2025] Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO☆73Updated 2 months ago
- [ECCV 2024] API: Attention Prompting on Image for Large Vision-Language Models☆107Updated last year
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention☆57Updated last year
- [NeurIPS 2024] Official PyTorch implementation of "Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives"☆46Updated last year
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆65Updated 6 months ago
- Adapting LLaMA Decoder to Vision Transformer☆30Updated last year
- Official Repository of Personalized Visual Instruct Tuning☆33Updated 9 months ago
- [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Di…☆61Updated last year
- ☆81Updated last year
- Official implement of MIA-DPO☆69Updated 11 months ago
- ☆46Updated last year
- Code for "AVG-LLaVA: A Multimodal Large Model with Adaptive Visual Granularity"☆32Updated last year
- Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types☆32Updated 5 months ago
- We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their…☆20Updated last year
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆48Updated last year
- An Enhanced CLIP Framework for Learning with Synthetic Captions☆39Updated 8 months ago
- [ECCV 2024] ControlCap: Controllable Region-level Captioning☆80Updated last year
- OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆44Updated 3 weeks ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆51Updated 6 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆83Updated 2 months ago
- Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning☆24Updated last year