iOPENCap / awesome-unimodal-trainingLinks
text-only training or language-free training for multimodal tasks (image/audio/video caption, retrieval, text2image)
☆11Updated last year
Alternatives and similar repositories for awesome-unimodal-training
Users that are interested in awesome-unimodal-training are comparing it to the libraries listed below
Sorting:
- Mitigating Open-Vocabulary Caption Hallucinations (EMNLP 2024)☆18Updated last year
- ☆11Updated 11 months ago
- ☆11Updated last year
- [EMNLP’24 Main] Encoding and Controlling Global Semantics for Long-form Video Question Answering☆18Updated last year
- Repo for paper "CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models".☆12Updated last year
- TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models☆19Updated 11 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆56Updated last year
- [ACL’24 Findings] Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives☆45Updated 5 months ago
- WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs☆34Updated last month
- ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs☆25Updated 4 months ago
- [ECCV'24] Official Implementation of Autoregressive Visual Entity Recognizer.☆14Updated last year
- Official Repo for FoodieQA paper (EMNLP 2024)☆16Updated 5 months ago
- ☆10Updated last year
- A hot-pluggable tool for visualizing LLaVA's attention.☆24Updated last year
- [CVPR 2024] Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension☆60Updated last year
- [IJCAI 2023] Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment☆53Updated last year
- An in-context learning research testbed☆19Updated 9 months ago
- This repo contains evaluation code for the paper "AV-Odyssey: Can Your Multimodal LLMs Really Understand Audio-Visual Information?"☆31Updated 11 months ago
- OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆42Updated last week
- Code for DeCo: Decoupling token compression from semanchc abstraction in multimodal large language models☆74Updated 5 months ago
- Noise of Web (NoW) is a challenging noisy correspondence learning (NCL) benchmark containing 100K image-text pairs for robust image-text …☆15Updated last month
- [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in…☆177Updated 2 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆125Updated 3 months ago
- [ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives☆39Updated 3 months ago
- Code and data for ACL 2024 paper on 'Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space'☆17Updated last year
- Code for paper: Unified Text-to-Image Generation and Retrieval☆16Updated last year
- CLIP-MoE: Mixture of Experts for CLIP☆50Updated last year
- [CVPR 2024] Do you remember? Dense Video Captioning with Cross-Modal Memory Retrieval☆63Updated last year
- This is the official implementation of RGNet: A Unified Retrieval and Grounding Network for Long Videos☆17Updated 9 months ago
- [NeurIPS 2025] The official repository of "Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tun…☆38Updated 10 months ago