Gemma 3

SL2T is our breakthrough sign language-to-text model powering new features for Deaf and hard of hearing users on @Android. Starting with American Sign Language-to-English on Pixel 11, people can sign

SL2T is our breakthrough sign language-to-text model powering new features for Deaf and hard of hearing users on @Android. Starting with American Sign Language-to-English on Pixel 11, people can sign directly into Gboard and Live Transcribe instead of typing. https://t.co/p9Vx7tJtLT

We sat down with Apollo 2 to talk about what it's really like running on Gemini Robotics 2. 🤖 https://t.co/PhxXMkMfBY

Predicting cyclones accurately can help save lives - and every hour of lead time counts. Published in @Nature, our AI model WeatherNext achieves state-of-the-art accuracy in forecasting a storm’s trac

Predicting cyclones accurately can help save lives - and every hour of lead time counts. Published in @Nature, our AI model WeatherNext achieves state-of-the-art accuracy in forecasting a storm’s track and intensity, giving us a critical extra 24 hours to prepare on average. 🧵 https://t.co/Noht1k1Zl7

Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings

Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens, journalists, and researchers. Applying Retrieval-Augmented Generation (RAG) to parliamentary transcripts introduces three specific risks: dominance of the most frequent speakers, inability to weight speakers according to topical expertise, and citation misattribution in politically sensitive text. We present ParliamentRAG, a RAG system for the Italian Chamber of Deputies that addresses these risks jointly. Its core contribution is a topic-dependent authority model that estimates each speaker's authority as a function of the current query, combining interpretable components such as profession, education, and previous interventions. Given a user query, the system retrieves relevant speech chunks, identifies topic-relevant experts across parliamentary groups, and generates a summary synthesizing their perspectives, accompanied by supporting quotations. ParliamentRAG is evaluated against Google NotebookLM on 15 policy topics via a two-level protocol combining automated metrics and blind A/B human evaluation by six domain experts. The system achieves higher coverage across political groups (0.97 vs. 0.95), perfect quotation faithfulness (1.00 vs. 0.95), and stronger expert preferences on source-related dimensions, while NotebookLM remains stronger on prose-oriented dimensions.

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and the two match on clustering, STS, and pair classification. Reaching that parity is expensive. An LLM costs up to 1,431x more than an embedding model of comparable quality (USD 154 vs. USD 0.11 per benchmark pass), and the open LLMs tested process tokens 2.5 to 736x more slowly on the same GPU. Reasoning tokens account for 28 to 81% of LLM inference cost; lower reasoning budgets preserve or improve retrieval quality for most models in our ablation. The Pareto frontier contains the leading embedding models and one LLM, Gemini 3.1 Pro. These results support a division of labour: use embedding models for similarity, classification, and clustering, and reserve LLMs for reasoning-intensive retrieval. Our code, datasets, and results are publicly available at https://github.com/embeddings-benchmark/embedders-dilemma.

Multimodal Model Diffing for Feature Discovery and Control

Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control. While applicable to post-hoc inspection, hidden states that are decomposed into interpretable feature directions using sparse autoencoders (SAEs) neither readily isolate which features are changed by multimodal training, nor are they directly useful for targeted control. We introduce MMDiff, a multimodal model-diffing framework that trains multimodal SAEs and turns them into feature-level interfaces for discovering and controlling multimodal behavior. MMDiff supports three uses: (i) feature isolation, by diffing a base-LM SAE against its multimodal-adapted counterpart to identify features altered by multimodal training; (ii) task-specific feature detection, via per-token contrastive firing analysis that isolates causal features; and (iii) feature-level control, by causally removing or steering the discovered feature directions. We train multimodal SAEs for three MLLM families, LLaVA-MORE, PaliGemma 2, and InternVL3.5, and evaluate on visual-spatial understanding, multimodal safety, and OCR. MMDiff discovers sparse, causally specific features whose removal selectively degrades target behaviors by an average of 12% on spatial tasks and 17% on OCR, and reduces attack success rate by 24% on multimodal safety attacks, with no impact on VQA performance. Steering these features improves spatial and OCR accuracy by +3.6% and +1.8% on average over a standard single-layer steering baseline. These results show that multimodal SAEs can serve not only as interpretability tools, but as mechanisms for auditing, steering, and controlling MLLMs behavior toward safer and more capable generations.

Energy-Guided Flow Matching

Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly. In this paper, we introduce Energy-Guided Flow Matching(EG-FM) that explicitly models a coarse-to-fine generative trajectory by moving endpoint. Specifically, EG-FM replaces the fixed endpoint with a heat-kernel-filtered endpoint that evolves smoothly from low-frequency image to clean image. The fraction of high-frequency signal in moving endpoint is released by an image-specific energy-guided scheduling, leading to the re-targeting of velocity in flow matching. Our framework requires no adaptation of the backbone and training data, bringing negligible cost on the training and inference stages. In our experiment, EG-FM consistently achieves lower FID on the ImageNet class-conditional image generation task at 256 times 256 with fewer epochs, reaching an FID of 1.55 at 200 epochs and 1.45 at 600 epochs. We continue training the generation task on the setting of 512 times 512 resolution, yielding a FID of 1.58 after only 40 high-resolution adaptation epochs. Furthermore, we transfer EG-FM on text-to-image generation and achieve 0.85 on GenEval score and 83.9 on DPG-Bench. Code is available at https://github.com/ysng123/EG-FM.

Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection

The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and multimodal large language models (MLLMs), whether operating as a single model or relying on a single analytical perspective, often fail to capture subtle forgery artifacts, limiting their generalization to emerging AI-generated methods. To address these limitations, we introduce FaceVid-Forensics-100K, a large-scale deepfake video dataset comprising 100,000 videos and spanning 33 synthesis methods across face swapping, face reenactment, and entire-face synthesis, including recent generators such as Seedance 2.0. The dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations, automatically synthesized through a multi-model aggregation and conflict-resolution pipeline powered by advanced MLLMs. Building on this benchmark, we propose a multi-agent forensic reasoning framework that employs four specialized domain-expert agents to independently analyze forgery cues from four perspectives: texture, lighting, motion, and physics. A judge agent then reconciles their reports to produce a final prediction together with an explanation. Extensive evaluations on out-of-domain test sets show that, despite being composed entirely of small open-source MLLMs, our framework outperforms all methods including closed-source GPT and Gemini models and ranks first across all reported metrics on this benchmark. The project page is available at https://xavierjiezou.github.io/ARGUS/.

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

gemma-3-27b-it — LiveBench Scores

language: 0.4 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5