論文まとめ：Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
298{icon} {views} タイトル：Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and […]...
論文まとめ：OmniGen: Unified Image Generation
282{icon} {views} タイトル：OmniGen: Unified Image Generation 著者：Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan […]...
論文まとめ：Unveiling Encoder-Free Vision-Language Models
580{icon} {views} タイトル：Unveiling Encoder-Free Vision-Language Models 著者：Haiwen Diao, Yufeng Cui, Xiaotong Li, […]...
論文まとめ：Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
1.1k{icon} {views} 論文URL：Video-LLaVA: Learning United Visual Representation by Alignment Before Projection 著者： […]...
MiniGPT-4をAutoGPTQ/BitsAndBytesで量子化時の生成文章の定量評価
511{icon} {views} LLMをデプロイする際に、LLM部分の量子化が必要になることが多いです。MiniGPT4のようなVLMに焦点をあて、AutoGPTQとBitsAndBytesという2つの量子化フレーム […]...