Vision Language Models http://www.semanlink.net/tag/vision_language_models Documents tagged with Vision Language Models LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR http://www.semanlink.net/doc/2025/10/lightonocr_1b_the_case_for_end 2025-10-23T18:32:40Z en python, comment créer une image à partir d'une page de site web http://www.semanlink.net/doc/2025/08/en_python_comment_creer_une_im 2025-08-27T14:27:03Z Manuel Faysse sur X : "Introducing ColQwen-Omni, a 3B omnimodal retriever that extends the ColPali concept of multimodal retrieval with late interaction to audio chunks and short videos..." http://www.semanlink.net/doc/2025/07/manuel_faysse_sur_x_introduc > The model is trained solely on visual document retrieval. Based on the Qwen-Omni backbone, it is able to generalize its newly learned document embedding capabilities to embed audios and short videos without ever having seen those during contrastive training! > We can thus do "**Retrieval in Audio Space**". It only takes 10s to embed 30 minutes of audio. > This is orders of magnitude faster than indexing based on STT transcriptions 2025-07-17T21:35:10Z LlamaIndex 🦙 sur X : "a new multilingual, open-source visual embedding model and training set on Huggingface..." http://www.semanlink.net/doc/2025/01/llamaindex_%F0%9F%A6%99_sur_x_we_ve_re 2025-01-11T14:40:36Z Tony Wu sur X : "ColPali is now live in 🤗 transformers!" http://www.semanlink.net/doc/2024/12/tony_wu_sur_x_colpali_is_now 2024-12-18T18:06:19Z Beyond Text: The Rise of Vision-Driven Document Retrieval for RAG | Vespa Blog http://www.semanlink.net/doc/2024/11/beyond_text_the_rise_of_vision 2024-11-10T10:15:36Z tonywu71/colpali-cookbooks: Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. 👨🏻‍🍳 http://www.semanlink.net/doc/2024/10/tonywu71_colpali_cookbooks_rec 2024-10-19T07:26:16Z 🍄 ColPali: Document Retrieval with Vision Language Models http://www.semanlink.net/doc/2024/10/%F0%9F%8D%84_colpali_document_retrieval_ 2024-10-06T23:19:52Z So Yeon (Tiffany) Min sur X : "Embodied-RAG, a General Non-Parametric Method for Retrieval and Generation..." http://www.semanlink.net/doc/2024/10/so_yeon_tiffany_min_sur_x_ > A new framework that equips embodied agents with a non-parametric memory capable of autonomously constructing hierarchical knowledge for navigation and language generation. ([Ruslan Salakhutdinov](tag:ruslan_salakhutdinov) [tweet](https://x.com/rsalakhu/status/1842694504387916073)) > Hi robot, I'm dehydrated, can you take me somewhere? > How to apply non-parametric memory to every day experiences? > key challenges in building embodied memory > - Dense memory that logs everything is memory inefficient. > - Space is continuous, and locations are spatially correlated, in contrast to independent documents in the text domain. > During the retrieval/generation phase, we select K "chains" (a leaf node all the way up to the root node), that are closest to the query. 2024-10-06T10:18:51Z [2406.11251] Unifying Multimodal Retrieval via Document Screenshot Embedding http://www.semanlink.net/doc/2024/09/2406_11251_unifying_multimoda > Document Screenshot Embedding} (DSE), a novel retrieval paradigm that regards document screenshots as a unified input format, which does not require any content extraction preprocess and preserves all the information in a document (e.g., text, image and layout) 2024-09-25T15:58:45Z ColPali — Revolutionizing multimodal document retrieval | by Simeon Emanuilov | Sep, 2024 | Medium http://www.semanlink.net/doc/2024/09/colpali_revolutionizing_multi 2024-09-20T23:16:53Z [2407.01449] ColPali: Efficient Document Retrieval with Vision Language Models http://www.semanlink.net/doc/2024/09/2407_01449_colpali_efficient 2024-09-07T13:56:46Z