The Archive

BERT-large fine-tuned on Gemma 4 annotations achieves 0.589 Kendall's τ for ordinal literary sentiment analysis.

Google's Suncatcher satellite data center prototype launched October 1; Gemma 4 executed inference in orbit.

Google's Project Suncatcher satellite successfully ran Gemma 4 inference on TPUs in orbit and transmitted response to Earth.

Google's space-based TPU running Gemma 4 demonstrates on-orbit AI inference capability for satellite data centers.

BYOD enables parameter-efficient LoRA conversion of autoregressive models (Gemma 2 9B, Llama 3.1 8B, Qwen2.5 7B, Ministral 8B) to diffusion language models.

LLM-agent opinion simulations on Qwen3, Llama-3.2, Gemma-3 fail complement consistency: p + (1-p) ≠ 1 when agents reason over own vs. neighbor states.

This paper describes our submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset created through task-preserving localisation, and CrossEuroAlpaca, a cross-lingual augmentation that assigns different source and target languages to instructions, contexts and responses. Our system targets open-ended question answering (QA-OEG) in ten shared-task languages represented in the auxiliary data. Under matched decoding, adaptation improves the mean Gemma-4 judge score on target-language Q...

Google DeepMind and GovTech Singapore deploy Gemma models on-device to detect conversational scams without cloud data transmission.

Google has released an experimental note-taking app that can transcribe meetings and audio files entirely offline, as reported earlier by TechCrunch. The app, called Google AI Edge Foresight, is free to use and runs on macOS using the company's on-device EmbeddingGemma 2 model. Similar to AI note-taking apps like Granola and Wispr Flow, Foresight summarizes your meetings while providing a space where you can take your own notes. Google says you can jot down shorthand bullet points during your meeting, and the app will transform them into "polished notes" based on the information in the transc...

Simon Willison praises EmbeddingGemma 2's Apache 2.0 license, arguing open-weight embedding models reduce vendor lock-in risk for production deployments.

Google DeepMind releases EmbeddingGemma 2, an open-weight multimodal embedding model for efficient retrieval and semantic search tasks.

Fine-tuned Gemma-3-12B matches GPT-4o on ICH entity extraction from radiology reports; compares discriminative vs. generative adaptation for open-weight models.

Bongard: open-weight System One model separating pattern recognition from judgment using T5Gemma 2 4B encoder-decoder.

Google AI's Gemma model featured in winning Future Vision XPRIZE trailer 'The Gifted'; promotional content without technical details.

Serving infrastructure (Ollama, Gemma, Phi) confounds tool-use evaluation results; model behavior inconsistency stems from serving layer gatekeeping.

Disaggregated quantization specializes compute formats for LLM prefill vs. decode phases; tested on Qwen 3 and Gemma 3.

Comparative evaluation of EmbeddingGemma and fine-tuned variants for semantic job-candidate matching via hybrid retrieval with reciprocal rank fusion.

Sparse autoencoders reveal Gemma-3 and Qwen3.5 contain encoded evidence for harmful meme detection but fail to route it to outputs, not lack evidence.

Google highlights Gemma model applications for societal impact across expert and community use cases.

Google outlines Gemma's role in accelerating scientific research and improving real-world outcomes.

Google extends Gemma multilingual capabilities beyond text translation to preserve nuance across world languages.

Evaluates edge-deployable 2–8B vision-language models (Qwen3-VL, Gemma3) versus BioCLIP on species identification from camera-trap imagery.

Layerwise intervention study reveals how Qwen, Llama, Gemma route query info and retrieve internal knowledge across layers during QA.

Google Search adds race registration alerts and training plan features for runners; unrelated to Gemma or frontier AI.

Google Search adds live sports tracking and fantasy recommendations via Gemma, a consumer feature integration.

Comparative analysis of worldbuilding strategies in AI-generated vs. human fiction across GPT-4, LLaMA 3.3, Mistral 3.2, Gemma 3.

Google announces August 2026 AI updates; article lacks specific details on Gemma releases or capabilities.

Google and Kaggle launched a free 353,000-person course on AI agents using Gemma, focused on building and deploying agent systems.

Benchmark of six VLMs (Gemini, GPT-4V, Qwen, Gemma, Llama, Ministral) on zero-shot anomaly detection for game geometry clipping in agent-driven QA.

Learned soft prefix attacks on syllogistic reasoning expose logical stability limits in Qwen, Gemma models under contextual pressure.