Image, video, audio, and text generation
Equity breaks down why OpenAI pulled the plug on Sora, what Meta’s back-to-back legal losses mean, and more of the week's headlines.
Watch as Equity asks why OpenAI shut down Sora just months after launch, what Meta’s back-to-back legal losses mean, and more of the week...
MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...
![[2603.19337] Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2603.19337: Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity
Abstract page for arXiv paper 2603.19280: From Feature-Based Models to Generative AI: Validity Evidence for Constructed Response Scoring
Abstract page for arXiv paper 2603.19263: How Motivation Relates to Generative AI Use: A Large-Scale Survey of Mexican High School Students
Fanvue, OpenArt, and ElevenLabs have launched an ‘AI Personality of the Year’ award to recognize the growing AI influencer economy.
Peter Holderrieth and Ezra Erives just released their new MIT 2026 course on flow matching and diffusion models! It introduces the full s...
AI was everywhere at the GDC Festival of Gaming this year, but developers I spoke with were strongly against using AI in their games.
Jewelry is one of the, if not the, hardest categories for AI image generation. Reflective metals, facet edges, prong geometry, and gemsto...
Modern generative models (Sora, Runway, Kling) still struggle with the complex physics of the shoreline. I’ve spent months capturing 116 ...
Ghost in the Machine — out on Kinema March 26th — director Valeria Veatch speaks with The Verge about gen AI’s roots in eugenics.
The OpenClaw frenzy has led to a new Nvidia product.
The generative AI models used in classified environments can answer questions, but don't currently learn from the data they see. Tha...
Abstract page for arXiv paper 2512.05106: NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation
Abstract page for arXiv paper 2509.24335: Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
Abstract page for arXiv paper 2509.21739: Noise-to-Notes: Diffusion-based Generation and Refinement for Automatic Drum Transcription
Abstract page for arXiv paper 2507.18534: Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
Abstract page for arXiv paper 2505.03858: Differentially Private and Scalable Estimation of the Network Principal Component
Abstract page for arXiv paper 2602.11590: Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
Abstract page for arXiv paper 2603.05396: Harnessing Synthetic Data from Generative AI for Statistical Inference
Abstract page for arXiv paper 2603.04638: Spinverse: Differentiable Physics for Permeability-Aware Microstructure Reconstruction from Dif...
Abstract page for arXiv paper 2603.04535: A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime