Nano Banana

MMAE: A Massive Multitask Audio Editing Benchmark

arXiv:2606.07229v1 Announce Type: new Abstract: We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing. Spurred by the shift toward intelligent creation, interactive editing has rapidly expanded from visual domains, pioneered by models like Nano-banana 2 for images and Gemini-Omni for video, into audio. However, the current evaluation infrastructure lags severely,...

Mitigating Content Shift and Hallucination in GenAI Image Editing via Structural Refinement

arXiv:2605.30437v1 Announce Type: new Abstract: Generative AI (GenAI) image editors, such as Nano Banana, produce visually compelling results for retouching tasks, enabling non-experts to edit images through text prompts alone. However, the generative nature of these models often introduces spatial misalignment, texture distortion, and content hallucination, all of which are detrimental to downstream workflows that require pixel-level fidelity. We identify a problem setting we call...

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Announce Type: replace Abstract: 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.

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

arXiv:2605.31039v1 Announce Type: new Abstract: 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.

Google shuts down the AI image app Pixel Studio

Google shuts down the AI image app Pixel Studio It launched less than two years ago. Google has shut down its Pixel Studio app with the latest update, according to a report by 9to5Google. The AI-powered image generation app launched less than two years ago and received a fairly substantial content update last year.

Image Generators are Generalist Vision Learners

Announce Type: replace Abstract: Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and reasoning from generative pretraining. While it has long been conjectured that the ability to create visual content implies an ability to understand it, there has been limited evidence that generative vision models have developed strong understanding capabilities.

South Korean Forums Will Need to Scan Every Images with AI Censorship Tools

Due to recent regulation changes (전기통신사업법), the South Korean government is requiring internet communities and forum owners to scan every user uploaded images and videos on their website, by AI. The hardware to run these AI models are also not provided by government, website owners have to buy datacenter grade Nvidia GPUs by themselves, putting financial pressure to small businesses and forums. Websites will need to implement these hardware and software features, starting immediately from...

Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models

Announce Type: replace Abstract: Scientific illustrations are essential tools for communicating research findings, especially in natural science, where they visualize complex concepts and processes. As Text-to-Image (T2I) models become increasingly capable, researchers have started to use them for scientific illustration generation. However, existing benchmarks often assess outputs at a holistic level, overlooking fine-grained elements, while scientific reasoning ability and output...

Threat hunters find Google API keys still usable 23 minutes after deletion

Google cuts the price of its AI Plus plan and doubles the storage

Google cuts the price of its AI Plus plan and doubles the storage The subscription now starts at $5 per month. Google is lowering the cost of its cheapest AI subscription to make Gemini models even easier to access. The Google AI Plus plan will now cost $5 per month, according to a post from Vikas Kansal, the company's Product Lead focused on Gemini AI subscriptions, down from its original $8 per month price.