Gemma 4 26B A4B IT

Some fun Gemini Omni use cases from the community 🧵👇

Look back at last week’s I/O announcements with @NotebookLM. You can listen to an audio overview, watch the video recap, and even check out our detailed slide deck summarizing all of the biggest news

Look back at last week’s I/O announcements with @NotebookLM. You can listen to an audio overview, watch the video recap, and even check out our detailed slide deck summarizing all of the biggest news and launches. Check it out here: https://t.co/AIhdaw05b9

Look back at last week’s I/O announcements with @NotebookLM. You can listen to an audio overview, watch the video recap, and even check out our detailed slide deck summarizing all of the biggest news

Look back at last week’s I/O announcements with @NotebookLM. You can listen to an audio overview, watch the video recap, and even check out our detailed slide deck summarizing all of the biggest news and launches. Check it out here: https://t.co/Zc69abPReX https://t.co/cXEu6AhnGV

Our Gemini for Science tools could help scientists unlock their next breakthrough. 🧬 https://t.co/ENTKmsIQp3

SynthID has already watermarked over 100 billion pieces of content, but transparency is a team sport. That’s why we’re partnering with @OpenAI, @ElevenLabs and Kakao to add SynthID watermarking to the

SynthID has already watermarked over 100 billion pieces of content, but transparency is a team sport. That’s why we’re partnering with @OpenAI, @ElevenLabs and Kakao to add SynthID watermarking to their models – accelerating the industry-wide momentum we started with @NVIDIA. https://t.co/QnshYx3EfE

JLT: Clean-Latent Prediction in Latent Diffusion Transformers

Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity. We ask whether this principle remains useful after images are mapped into a learned latent space, where compression has already removed much of the raw pixel variability. We introduce JLT, a 130M latent diffusion Transformer over frozen FLUX.2 VAE codes, and compare clean-latent prediction with a matched velocity-prediction DiT under the same representation, backbone, and training settings. Although the three variables x, epsilon, and v are linearly convertible for a fixed corruption time, a local Gaussian analysis shows that velocity regression inherits an isotropic target-covariance floor and amplifies low-variance latent directions, while clean prediction damps them. On ImageNet 256 x 256, JLT-B/1 obtains FID-50K 2.50 with classifier-free guidance, with a large matched-target gap over velocity prediction. These results suggest that prediction targets in latent diffusion are representation-dependent geometric choices, rather than interchangeable algebraic parameterizations.

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.

Cross-scale Aligned Supervision for Training GANs

Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-fine hierarchical generation. In this work, we challenge this interpretation. We argue that standard scale-wise adversarial supervision does not construct a proper coarse-to-fine hierarchy: each intermediate image is independently pushed toward the real distribution at its own resolution, but this scale-wise realism does not ensure that outputs across stages represent the identical generated sample. Moreover, the scale-specific image produced at each stage is not used as an explicit refinement target for the subsequent stage. Therefore, its adversarial loss can improve a scale-specific output without constraining later stages to preserve the same sample trajectory, allowing them to move toward a different sample rather than refine the previous output. We refer to this problem as a cross-scale trajectory misalignment problem. To resolve it, we propose CAT, a Cross-scale Aligned Transformer for multi-scale adversarial generation. CAT keeps the discriminator scale-wise, so each intermediate output is evaluated at its own resolution, while adding a simple generator-side consistency regularization that aligns intermediate outputs with the final output. On class-conditional ImageNet-256, CAT-H/2 achieves an FID-50K of 1.56 with one-step inference after only 60 training epochs, outperforming strong one-step GAN and diffusion/flow baselines.

Gemma 4 26B A4B IT is now available on Ollama

Gemma 4 26B A4B IT is now available through local Ollama runtime. 128K context window listed. Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

google/gemma-4-26B-A4B-it · Hugging Face

Google published benchmark or leaderboard evidence for gemma-4-26B-A4B-it.

Gemma 4 open deployment launch

Google launched Gemma 4 under Apache 2.0 and positioned it for private deployment on your own hardware, cloud GPUs, and edge devices.

Gemma 4: Byte for byte, the most capable open models

Gemma 4: our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.

Gemma 4: Byte for byte, the most capable open models

Purpose-built for advanced reasoning and agentic workflows, Gemma 4 delivers an unprecedented level of intelligence-per-parameter. Open model performance vs size on Arena.ai ’s chat arena as of 4/1. The entire family moves beyond simple chat to handle complex logic and agentic workflows.