FreedomIntelligence / TRIMLinks
We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.
☆20Updated last year
Alternatives and similar repositories for TRIM
Users that are interested in TRIM are comparing it to the libraries listed below
Sorting:
- [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Di…☆61Updated last year
- The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…☆84Updated 11 months ago
- Preference Learning for LLaVA☆58Updated last year
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)☆51Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆83Updated 2 months ago
- [ACM Multimedia 2025] This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual…☆82Updated 10 months ago
- An Enhanced CLIP Framework for Learning with Synthetic Captions☆38Updated 8 months ago
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆48Updated last year
- The released data for paper "Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models".☆34Updated 2 years ago
- Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".☆58Updated 2 years ago
- Implementation and dataset for paper "Can MLLMs Perform Text-to-Image In-Context Learning?"☆42Updated 6 months ago
- This repository contains the code of our paper 'Skip \n: A simple method to reduce hallucination in Large Vision-Language Models'.☆15Updated last year
- Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning☆24Updated last year
- Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models (ACL-Findings 2024)☆16Updated last year
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆86Updated 3 months ago
- Official repository for CoMM Dataset☆48Updated 11 months ago
- Official Repository of Personalized Visual Instruct Tuning☆33Updated 9 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆70Updated last year
- VideoHallucer, The first comprehensive benchmark for hallucination detection in large video-language models (LVLMs)☆41Updated last week
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆83Updated last year
- ☆17Updated last year
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆65Updated 6 months ago
- ☆18Updated last year
- Official code for "pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation", ICML 2023.☆33Updated 2 years ago
- Official implementation of our paper "Finetuned Multimodal Language Models are High-Quality Image-Text Data Filters".☆69Updated 8 months ago
- COLA: Evaluate how well your vision-language model can Compose Objects Localized with Attributes!☆25Updated last year
- Matryoshka Multimodal Models☆121Updated 11 months ago
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆76Updated last year
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆53Updated 9 months ago
- [CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"☆50Updated 6 months ago