DataGemma
Unknown
DataGemma reduces LLM hallucinations by grounding responses in Google's Data Commons statistical database using RIG and RAG methods.
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
DataGemma reduces LLM hallucinations by grounding responses in Google's Data Commons statistical database using RIG and RAG methods.
Unknown
ShieldGemma is a suite of LLM-based safety content moderation models built on Gemma2 that predict safety risks across key harm types in user input and LLM-generated output.
Unknown
Proposes a scalable and domain-general abstractive proposition segmentation model by training LLMs on synthetic multi-domain data.
Unknown
ColPali uses PaliGemma to generate contextualized embeddings from document page images for efficient visually rich retrieval via late interaction.
Neha Yadav, S. Pande, A. Ranjith kumar
Combines SigLIP vision model and Gemma language model following PaLI-3 recipe for strong vision-language task performance.
Deepon Halder, Angira Mukherjee
Fine-tunes Gemma3–4B-IT to create a translation model supporting 22 Indian languages.
Unknown
Gemma 3 is a multimodal language model with vision understanding, 128k context, and improved performance via distillation and a novel post-training recipe.
Unknown
Gemma 2 improves open language models by interleaving local-global attention and using knowledge distillation, achieving competitive performance with much larger models.
Unknown
Introduces Gemma, a family of 2B and 7B state-of-the-art language models derived from Google's Gemini, with advances in language understanding, reasoning, and safety.