Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human feedback to mitigate these problems and refine the video generation model. Specifically, we begin by constructing a large-scale human preference dataset focused on modern video generation models, incorporating pairwise annotations across multi-dimensions. We then introduce VideoReward, a multi-dimensional video reward model, and examine how annotations and various design choices impact its rewarding efficacy. From a unified reinforcement learning perspective aimed at maximizing reward with KL regularization, we introduce three alignment algorithms for flow-based models. These include two training-time strategies: direct preference optimization for flow (Flow-DPO) and reward weighted regression for flow (Flow-RWR), and an inference-time technique, Flow-NRG, which applies reward guidance directly to noisy videos. Experimental results indicate that VideoReward significantly outperforms existing reward models, and Flow-DPO demonstrates superior performance compared to both Flow-RWR and supervised fine-tuning methods. Additionally, Flow-NRG lets users assign custom weights to multiple objectives during inference, meeting personalized video quality needs.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

PCWorld reports that Mozilla has redesigned Firefox's settings menu with clearer category groupings and an improved search function for easier navigation. The update removes the classic'General' page and reorganizes existing settings into new sections while preserving user configurations. This redesign aims to create a more intuitive experience for Firefox users seeking specific browser settings and features. Mozilla has redesigned its settings interface for its Firefox browser. The aim is to make it easier to navigate features such as privacy, AI settings, tab management, language, and appearance.

Large language models (LLMs) are powerful tools capable of handling diverse tasks. Comparing and selecting appropriate LLMs for specific tasks requires systematic evaluation methods, as models exhibit varying capabilities across different domains. However, finding suitable benchmarks is difficult given the many available options. This complexity not only increases the risk of benchmark misuse and misinterpretation but also demands substantial effort from LLM users, seeking the most suitable benchmarks for their specific needs. To address these issues, we introduce BenchmarkCards, an intuitive and validated documentation framework that standardizes critical benchmark attributes such as objectives, methodologies, data sources, and limitations. Through user studies involving benchmark creators and users, we show that BenchmarkCardscan simplify benchmark selection and enhance transparency, facilitating informed decision-making in evaluating LLMs.

Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all available models simultaneously, with weight interpolation-based methods being the predominant approach. However, these conventional approaches are not well-suited for scenarios where models become available sequentially, and they often suffer from high memory requirements and potential interference between tasks. In this study, we propose a training-free projection-based continual merging method that processes models sequentially through orthogonal projections of weight matrices and adaptive scaling mechanisms. Our method operates by projecting new parameter updates onto subspaces orthogonal to existing merged parameter updates while using an adaptive scaling mechanism to maintain stable parameter distances, enabling efficient sequential integration of task-specific knowledge. Our approach maintains constant memory complexity to the number of models, minimizes interference between tasks through orthogonal projections, and retains the performance of previously merged models through adaptive task vector scaling. Extensive experiments on CLIP-ViT models demonstrate that our method achieves a 5-8% average accuracy improvement while maintaining robust performance in different task orderings. Code is publicly available at https://github.com/tanganke/opcm/.

'Ringleader' of alleged UFC drone attack to kill Trump is unmasked as illegal migrant who was granted DACA stay under Obama Watch horrifying drone video that follows woman's plunge to death after bungee team threw her from bridge without rope Horrific new videos blow Texas woman's mystery death wide open: Her agonizing'final gasp'... unthinkably vile corpse claims... and sick past of man who saw her last Taylor Swift's bottomless thirst for attention, her greed and sheer tackiness are now truly unbearable... this latest stunt has shown her true colors: MAUREEN CALLAHAN Spy world panic as Tulsi Gabbard prepares to unleash bombshell file dumps on secret CIA'mind control' project and Dr. Fauci Olivia Wilde, 42, complains about being on Maxim's Hot 100 List calling it the'most f***** up thing in the world' Has Taylor Swift already revealed her wedding dress designer? All my friends are suddenly getting divorced. Mid-life wives share taboo sex confessions about why they really leave... including common position that made one hate her husband: JANA HOCKING Kanye West's wife Bianca Censori raises eyebrows in plunging white lace lingerie as she photographs a nude model at Art Basel in Switzerland Knicks set to come face to face with Trump after president was'thunderously booed' at NBA Finals game Sensational REAL reason Jelly Roll is divorcing Bunnie XO: Insiders reveal'preacher's wife' bombshell that's the talk of Nashville... truth about legendary rocker cuckolding rumor... and G-string mishap Teen tourist thrown to death by Central Park horse was trying to save mom who flew out of carriage during family's first visit to Big Apple Father keeps his cool as shouting man calls cops on him for taking his two young daughters into women's restroom Trump privately frets Bibi Netanyahu's zeal to'bomb everyone' could turn him into another disgraced president'Moscow will burn', Zelensky vows as Russia's capital is blanketed in toxic smoke following huge Ukraine drone attack He drove a Rolls-Royce and lived the American dream. But behind the Gucci was the ATF's most unlikely secret weapon. MORE: Meteorologist reveals America's most dangerous cities in super El Niño's'corridor of chaos'... and warns this is only the beginning As many as 40 million people across eight states are in the deadly path of Tropical Storm Arthur after the first named storm of hurricane season made landfall Wednesday night.

PCWorld reports that Microsoft's new Outlook app for Windows 11 now supports adding email attachments while offline, with messages automatically sending once internet reconnects. This update addresses a key limitation for users who frequently work without reliable internet connections or need to prepare emails in advance. Despite these improvements, many users continue preferring the classic Outlook or web version over Microsoft's repackaged web app approach. For several years, Microsoft has been trying to persuade users to move from the classic Outlook app for Windows 11 to the new version, which is (essentially) a repackaged web app. The latest update offers improved offline support, making it possible to add attachments to emails without an internet connection. The emails will send automatically once you've got a working connection again. According to Windows Latest, Microsoft has been testing this feature since October 2025, with a wider rollout only now beginning. Although the "new" Outlook has improved recently, many still prefer the classic app or the web version. This article originally appeared on our sister publication PC för Alla and was translated and localized from Swedish.

Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results--such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with UniLumos, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow-matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose LumosBench, a disentangled attributelevel benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

We use a resampler-based embedding predictor [30], denoted as Plat each layer l, to output predictions.