After launching in October in the US and Canada via invitation only, OpenAI's video app, Sora 2, hit 1m downloads in just five days. After launching in October in the US and Canada via invitation only, OpenAI's video app, Sora 2, hit 1m downloads in just five days. The video app can produce realistic deepfakes of Marx shopping and MLK Jr trolling. Some say using'historical figures' is the company's way of testing the legal waters L ast night I was flicking through a dating app. One guy stood out: "Henry VIII, 34, King of England, nonmonogamy".

Many will assume that OpenAI's Sora app represents a new era of social media. But that's wrong--all it does is reanimate our current one. As a purely creative instrument, Sora, the new AI video app from OpenAI, is a game changer. Dream up any scenario and it appears in an instant. Mr. Rogers teaching Tupac Shakur the lyrics to the legendary rap diss "Hit Em Up."

Like many nascent artistic movements, generative AI art has been widely criticized. But some artists are nevertheless pushing the creative limits of these new tools. In this era of AI slop, the idea that generative AI tools like Midjourney and Runway could be used to make art can seem absurd: What possible artistic value is there to be found in the likes of Shrimp Jesus and Ballerina Cappuccina? But amid all the muck, there are people using AI tools with real consideration and intent. Some of them are finding notable success as AI artists: They are gaining huge online followings, selling their work at auction, and even having it exhibited in galleries and museums. "Sometimes you need a camera, sometimes AI, and sometimes paint or pencil or any other medium," says Jacob Adler, a musician and composer who won the top prize at the generative video company Runway's third annual AI Film Festival for his work Total Pixel Space "It's just one tool that is added to the creator's toolbox."

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .

This long-duration comet will make its closest approach to Earth this fall, before disappearing into the outer solar system for another 1,000 years. Comet Lemmon (C/2025 A6) photographed in Texas in late September 2025. It was early January 2025 when a faint light spot was observed at the Mt. Follow-up observations revealed that the object was a comet visiting from the outer edge of the solar system, and it was named Comet Lemmon (C/2025 A6). Its "period"--the time it takes to complete its lengthy orbit of the sun--is about 1,350 years.

Taylor Swift fans are driving a surge in popularity of a German museum exhibiting a portrait of the Shakespeare character Ophelia, recently reimagined in a song and music video from Swift's new album The Life of a Showgirl. The Hessische Landesmuseum in the central German city of Wiesbaden saw hundreds more visitors than usual over the weekend, as fans hoped to see the real version of the painting that opens the music video for The Fate of Ophelia. In the video, viewed more than 65 million times on Youtube, the painting comes alive, with Swift at its centre. We're really enjoying this attention - it's a lot of fun, museum spokesperson Susanne Hirschmann told the Associated Press. Hirschmann said that one family had travelled from the northern city of Hamburg, a five-hour drive away, while some of the visitors were Americans from an army base nearby.

Large language models (LLMs) have recently shown strong reasoning abilities in domains like mathematics, coding, and scientific problem-solving, yet their potential for ranking tasks, where prime examples include retrieval, recommender systems, and LLM routing, remains underexplored. Ranking requires complex reasoning across heterogeneous candidates, but existing LLM-based rankers are often domain-specific, tied to fixed backbones, and lack iterative refinement, limiting their ability to fully exploit LLMs' reasoning potential. To address these challenges, we propose R1-Ranker, a reasoning-incentive framework built on reinforcement learning, with two complementary designs: DRanker, which generates full rankings in one shot, and IRanker, which decomposes ranking into an iterative elimination process with step-wise rewards to encourage deeper reasoning. We evaluate unified R1-Rankers on nine datasets spanning recommendation, routing, and passage ranking, showing that IRanker-3B consistently achieves state-of-the-art performance, surpasses larger 7B models on some tasks, and yields a 15.7% average relative improvement. Ablation and generalization experiments further confirm the critical role of reinforcement learning and iterative reasoning, with IRanker-3B improving zero-shot performance by over 9% on out-of-domain tasks and reasoning traces boosting other LLMs by up to 22.87%. These results demonstrate that unifying diverse ranking tasks with a single reasoning-driven foundation model is both effective and essential for advancing LLM reasoning in ranking scenarios.

Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive process that identifies 75 chart types, 440 chart variations, and 68 layout templates from real infographic charts and uses them to create synthetic ones programmatically. We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation. By capturing the visual and structural complexity of real design, ChartGalaxy provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.

We present an inference-time diffusion sampling method to perform multi-view consistent image editing using pre-trained 2D image editing models. These models can independently produce high-quality edits for each image in a set of multi-view images of a 3D scene or object, but they do not maintain consistency across views. Existing approaches typically address this by optimizing over explicit 3D representations, but they suffer from a lengthy optimization process and instability under sparse view settings. We propose an implicit 3D regularization approach by constraining the generated 2D image sequences to adhere to a pre-trained multi-view image distribution. This is achieved through coupled diffusion sampling, a simple diffusion sampling technique that concurrently samples two trajectories from both a multi-view image distribution and a 2D edited image distribution, using a coupling term to enforce the multi-view consistency among the generated images. Diffusion-based image editing models have demonstrated unprecedented realism across diverse tasks via end-to-end training. However, collecting and curating 3D data is significantly more costly than working with 2D data. As a result, recent research has explored test-time optimization methods for multi-view editing that leverage pre-trained 2D image diffusion models (Poole et al., 2023; Haque et al., 2023). Figure 1: Applications of coupled diffusion sampling. Our approach enables lifting off-the-shelf 2D editing models into multi-view by combining the sampling process of 2D diffusion models with multi-view diffusion models to produce view-consistent edits.

Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such naturally occurring pairs are hard to curate at scale. Current workarounds use synthetic training pairs that leverage the zero-shot capabilities of existing models. However, this can propagate and magnify the artifacts of the pretrained model into the final trained model. In this work, we present a new training paradigm that eliminates the need for paired data entirely. Our approach directly optimizes a few-step diffusion model by unrolling it during training and leveraging feedback from vision-language models (VLMs). For each input and editing instruction, the VLM evaluates if an edit follows the instruction and preserves unchanged content, providing direct gradients for end-to-end optimization. To ensure visual fidelity, we incorporate distribution matching loss (DMD), which constrains generated images to remain within the image manifold learned by pretrained models. We evaluate our method on standard benchmarks and include an extensive ablation study. Without any paired data, our method performs on par with various image editing diffusion models trained on extensive supervised paired data, under the few-step setting. Given the same VLM as the reward model, we also outperform RL-based techniques like Flow-GRPO.