view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 14 days ago • 89
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data +7 Jun 3 • 302
view article Article nanoVLM: The simplest repository to train your VLM in pure PyTorch +5 May 21 • 247
view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM +2 Mar 12 • 480
view article Article PaliGemma 2 Mix - New Instruction Vision Language Models by Google +1 Feb 19 • 74