FreedomIntelligence / TRIMLinks
We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.
☆15Updated 11 months ago
Alternatives and similar repositories for TRIM
Users that are interested in TRIM are comparing it to the libraries listed below
Sorting:
- Preference Learning for LLaVA☆54Updated last year
- [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Di…☆59Updated last year
- The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…☆84Updated 9 months ago
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆49Updated last year
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆48Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆80Updated 3 weeks ago
- [ACM Multimedia 2025] This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual…☆82Updated 8 months ago
- Implementation and dataset for paper "Can MLLMs Perform Text-to-Image In-Context Learning?"☆41Updated 5 months ago
- An Enhanced CLIP Framework for Learning with Synthetic Captions☆37Updated 7 months ago
- The released data for paper "Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models".☆34Updated 2 years ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆81Updated last month
- [Arxiv] Aligning Modalities in Vision Large Language Models via Preference Fine-tuning☆88Updated last year
- Repository for the paper: dense and aligned captions (dac) promote compositional reasoning in vl models☆27Updated last year
- Official implementation of our paper "Finetuned Multimodal Language Models are High-Quality Image-Text Data Filters".☆67Updated 7 months ago
- ☆24Updated 5 months ago
- Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".☆58Updated 2 years ago
- Official Repository of Personalized Visual Instruct Tuning☆32Updated 8 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆65Updated 5 months ago
- Matryoshka Multimodal Models☆115Updated 9 months ago
- VideoHallucer, The first comprehensive benchmark for hallucination detection in large video-language models (LVLMs)☆38Updated 3 weeks ago
- [ICLR 23] Contrastive Aligned of Vision to Language Through Parameter-Efficient Transfer Learning☆40Updated 2 years ago
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆57Updated last year
- Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning☆23Updated last year
- [ICLR2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models☆89Updated last year
- ☆91Updated last year
- [MM2024, oral] "Self-Supervised Visual Preference Alignment" https://arxiv.org/abs/2404.10501☆59Updated last year
- ☆44Updated last year
- ☆50Updated 2 years ago
- [NeurIPS 2025] Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO☆60Updated 2 weeks ago
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆50Updated 8 months ago