neulab / PangeaLinks
This is the repo for the paper "PANGEA: A FULLY OPEN MULTILINGUAL MULTIMODAL LLM FOR 39 LANGUAGES"
☆112Updated 3 months ago
Alternatives and similar repositories for Pangea
Users that are interested in Pangea are comparing it to the libraries listed below
Sorting:
- (WACV 2025 - Oral) Vision-language conversation in 10 languages including English, Chinese, French, Spanish, Russian, Japanese, Arabic, H…☆82Updated 2 months ago
- This project is a collection of fine-tuning scripts to help researchers fine-tune Qwen 2 VL on HuggingFace datasets.☆74Updated 2 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆53Updated 9 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆116Updated 2 months ago
- ☆67Updated last year
- This is the official repository for Inheritune.☆115Updated 7 months ago
- ☆56Updated 10 months ago
- ☆87Updated last year
- ☆55Updated 7 months ago
- ☆70Updated 10 months ago
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆211Updated 9 months ago
- Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs☆90Updated 11 months ago
- ☆70Updated last year
- [EMNLP 2025] Distill Visual Chart Reasoning Ability from LLMs to MLLMs☆55Updated last month
- ☆155Updated last year
- ☆67Updated 6 months ago
- A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.☆96Updated 9 months ago
- ACL 2025: Synthetic data generation pipelines for text-rich images.☆137Updated 7 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- Python Library to evaluate VLM models' robustness across diverse benchmarks☆213Updated 3 weeks ago
- ☆74Updated last year
- Source code of the paper: RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering [F…☆68Updated last year
- ☆159Updated 2 months ago
- The open-source code of MetaStone-S1.☆108Updated 2 months ago
- [ACL2025 Findings] Benchmarking Multihop Multimodal Internet Agents☆46Updated 7 months ago
- Parameter-efficient finetuning script for Phi-3-vision, the strong multimodal language model by Microsoft.☆58Updated last year
- ☆50Updated 4 months ago
- ☆13Updated 9 months ago
- [ACL 2024 Findings & ICLR 2024 WS] An Evaluator VLM that is open-source, offers reproducible evaluation, and inexpensive to use. Specific…☆77Updated last year
- Code for KaLM-Embedding models☆93Updated 3 months ago