Gemini 3.1 image-focused model for high-fidelity prompt-following image generation and faster advanced editing. Brings Nano Banana Pro-level quality and reasoning to the faster Flash tier.
Model updates refreshed3d agoJul 10, 2026news + changelog
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
LaunchesGoogle3d ago
Step into the map with the Street View grounding feature in Project Genie from @GoogleDeepmind and @GoogleLabs. Announced at I/O, this research prototype uses locations from @GoogleMaps Street View as
Step into the map with the Street View grounding feature in Project Genie from @GoogleDeepmind and @GoogleLabs. Announced at I/O, this research prototype uses locations from @GoogleMaps Street View as a foundation, letting you generate and explore interactive, 360-degree virtual https://t.co/aixoHdiLmG
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that ad
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that adds a hidden digital watermark to AI content. Here’s a summary of SynthID’s https://t.co/6ZJCsdwuHK
🏛️ We’re unveiling a new way to converse with the ancient world. By grounding Gemini directly in our expert models Aeneas and Ithaca, our Predicting the Past Skill in Google @antigravity lets histori
🏛️ We’re unveiling a new way to converse with the ancient world. By grounding Gemini directly in our expert models Aeneas and Ithaca, our Predicting the Past Skill in Google @antigravity lets historians study Greek and Latin texts using plain English. 🧵 https://t.co/WQbUEyw8av
As @Apptronik expands their Robot Park facility, our research partnership means real-world data collected by the latest Apollo 2 humanoid platform will help train and advance Gemini Robotics. 🤖 Find
As @Apptronik expands their Robot Park facility, our research partnership means real-world data collected by the latest Apollo 2 humanoid platform will help train and advance Gemini Robotics. 🤖 Find out more → https://t.co/mo9QykKn4H https://t.co/5Ena9WLlJ9
AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarchically as conditional soft-label prediction over empirical annotator distributions. Our system maps fixed Gemini Embedding 2 vision-language representations through a lightweight Gated MLP trained with KL divergence and homoscedastic uncertainty weighting. Our submissions ranked first on Task 2.3 and fourth on Tasks 2.1 and 2.2 on the official Soft-Soft leaderboards. The code is available at https://github.com/NLP-AI-Wizards/EXIST-2026
A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝 On the latest episode of our podcast, host @fryrsquared sits down with @NeelNanda5 to explore interpretabil
A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝 On the latest episode of our podcast, host @fryrsquared sits down with @NeelNanda5 to explore interpretability – the science of reverse engineering how neural networks learn and think. https://t.co/JWHFnzzrOD
Step into the map with the Street View grounding feature in Project Genie from @GoogleDeepmind and @GoogleLabs. Announced at I/O, this research prototype uses locations from @GoogleMaps Street View as
Step into the map with the Street View grounding feature in Project Genie from @GoogleDeepmind and @GoogleLabs. Announced at I/O, this research prototype uses locations from @GoogleMaps Street View as a foundation, letting you generate and explore interactive, 360-degree virtual https://t.co/aixoHdiLmG
X/Twitter@GoogleDeepMindGoogleresearchresearch6d ago
🏛️ We’re unveiling a new way to converse with the ancient world. By grounding Gemini directly in our expert models Aeneas and Ithaca, our Predicting the Past Skill in Google @antigravity lets histori
🏛️ We’re unveiling a new way to converse with the ancient world. By grounding Gemini directly in our expert models Aeneas and Ithaca, our Predicting the Past Skill in Google @antigravity lets historians study Greek and Latin texts using plain English. 🧵 https://t.co/WQbUEyw8av
X/Twitter@GoogleDeepMindGoogleresearchresearch1w ago
As @Apptronik expands their Robot Park facility, our research partnership means real-world data collected by the latest Apollo 2 humanoid platform will help train and advance Gemini Robotics. 🤖 Find
As @Apptronik expands their Robot Park facility, our research partnership means real-world data collected by the latest Apollo 2 humanoid platform will help train and advance Gemini Robotics. 🤖 Find out more → https://t.co/mo9QykKn4H https://t.co/5Ena9WLlJ9
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that ad
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that adds a hidden digital watermark to AI content. Here’s a summary of SynthID’s https://t.co/6ZJCsdwuHK
AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarchically as conditional soft-label prediction over empirical annotator distributions. Our system maps fixed Gemini Embedding 2 vision-language representations through a lightweight Gated MLP trained with KL divergence and homoscedastic uncertainty weighting. Our submissions ranked first on Task 2.3 and fourth on Tasks 2.1 and 2.2 on the official Soft-Soft leaderboards. The code is available at https://github.com/NLP-AI-Wizards/EXIST-2026
SiamJEPA: On the Role of Siamese Student Encoders in JEPA
Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning. Unlike masked autoencoders that reconstruct pixels, JEPA models learn representations by predicting latent embeddings of masked regions. Existing JEPA-based methods, such as I-JEPA and V-JEPA, typically employ a single encoder in the student network. In contrast, using Siamese encoders for student network is more naturally aligned with brain-inspired representation learning frameworks, yet their role in JEPA models remains largely unexplored. In this paper, we investigate the effect of Siamese student encoders in JEPA-based representation learning. To this end, we propose SiamJEPA, masked Siamese student encoders equipped with an exponential moving average (EMA) teacher network. SiamJEPA can also be viewed as a JEPA formulation of the brain-inspired representation learning model PhiNet. Through extensive experiments on ImageNet linear probing, we demonstrate that Siamese encoders act as an effective regularizer for the JEPA objective, improving representation separability and accelerating learning during the early stages of training. Furthermore, SiamJEPA consistently outperforms comparable single-encoder JEPA variants under limited training budgets and achieves higher linear probing accuracy than Masked Autoencoders (MAE) which requires longer training. Our findings reveal that Siamese student encoders are not merely an architectural choice but constitute an important inductive bias for predictive representation learning. These results provide new insights into the design of JEPA-based models and suggest that incorporating Siamese student architectures offers a simple yet effective approach for improving self-supervised representation learning.
Representation Distribution Matching for One-Step Visual Generation
We elucidate the design space of Representation Distribution Matching (RDM), our name for the paradigm that trains a one-step image generator by matching generated and reference feature distributions under frozen pretrained encoders. We identify two design axes, how the distributions are compared and the representations they are compared in, and controlled studies along them yield three findings. First, the classical MMD, which could not train convincing generators a decade ago, becomes a strong and scalable objective once estimated right. Second, the generated batch is then the operative variable, with an optimum above 2048, far beyond customary batch sizes. Third, any single representation can be gamed, driven below the real score while images stay visibly fake, so we match against a balanced battery of encoders and evaluate with SW_r14, a Sliced-Wasserstein distance over 14 encoders that is independent of the training loss and resists gaming. Combining the preferred choices yields improved RDM (iRDM): it sets the one-step state of the art on ImageNet at SW_r14 1.30, corroborated by PickScore, a human-preference proxy our objective never optimizes, which prefers it over the prior best one-step generator on 71.2% of matched samples. The same recipe post-trains the four-step FLUX.2 [klein] into a one-step generator, surpassing the four-step version on GenEval, 0.826 to 0.794, and on PickScore, 22.76 to 22.58, in 90 H200 GPU-hours. Project page: https://alan-lanfeng.github.io/rdm/.
From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself. However, the mechanism behind the improvement from SRA to Self-Flow, dual-time scheduling, remains under-examined: Self-Flow attributes its gain to interactions between tokens at different noise levels, where cleaner tokens help infer noisier ones. In this work, we revisit this explanation and ask whether the gain instead comes from data augmentation along the noise dimension. To disentangle these factors, we introduce Attention Separation, which preserves the same dual-timestep input as Self-Flow while blocking attention between tokens assigned to different noise levels. Surprisingly, removing such interaction does not degrade performance and can even improve it, suggesting that the improvement from SRA to Self-Flow mainly comes from data augmentation. Furthermore,We show that Attention Separation itself provides an augmentation effect by splitting a single image into multiple effective training parts to expand the training data. Based on these observations, we combine self-representation alignment with dual-timestep and attention-separation augmentation, and demonstrate the effectiveness of this design on ImageNet.
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many reference patches produce close-to-zero runtime changes. Second, we show that public submission rankings depend strongly on the benchmark scoring rule. Among eight public submissions shared by GSO and SWE-fficiency, the official rankings disagree on 9 of 28 pairwise submission comparisons, and SWE-fficiency's leaderboard scoring rule assigns the worst ten tasks overly high score weights of 58.5%-82.8%. Third, looking across 10 public submissions for each task, we find that at least one submission matches or beats the reference patch on 85.3% (384/450) of replay-valid GSO and SWE-fficiency tasks, and beats the unoptimized base code on 99.8% (449/450). Our study complements leaderboard scores by identifying tasks with more reliable performance signals, quantifying per-task score contributions, and exposing the remaining performance gaps that are hidden by aggregate rankings.
GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration
Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models.
GEMS: Agent-Native Multimodal Generation with Memory and Skills
Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose GEMS (Agent-Native Multimodal GEneration with Memory and Skills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits.
