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...
![[2603.21208] JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2603.21208: JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
Abstract page for arXiv paper 2603.20700: mmWave-Diffusion:A Novel Framework for Respiration Sensing Using Observation-Anchored Condition...
Abstract page for arXiv paper 2603.21621: Proximal Policy Optimization in Path Space: A Schrödinger Bridge Perspective
Abstract page for arXiv paper 2603.21315: FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models
Abstract page for arXiv paper 2603.21210: Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
Abstract page for arXiv paper 2603.20987: Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers
Abstract page for arXiv paper 2603.20645: Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
Abstract page for arXiv paper 2603.20589: Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisf...
Abstract page for arXiv paper 2603.20418: Data-driven discovery of roughness descriptors for surface characterization and intimate contac...
Abstract page for arXiv paper 2603.14093: Not All Latent Spaces Are Flat: Hyperbolic Concept Control
Abstract page for arXiv paper 2603.13733: Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control
Abstract page for arXiv paper 2601.22725: OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
Abstract page for arXiv paper 2601.16296: Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing
Abstract page for arXiv paper 2601.08104: High-Fidelity Modeling of Stochastic Chemical Dynamics on Complex Manifolds: A Multi-Scale SIRE...
Abstract page for arXiv paper 2601.05848: Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
Abstract page for arXiv paper 2601.00834: Intrinsic-Metric Physics-Informed Neural Networks (IM-PINN) for Reaction-Diffusion Dynamics on ...
Abstract page for arXiv paper 2512.13157: Intrinsic Image Fusion for Multi-View 3D Material Reconstruction
Abstract page for arXiv paper 2512.11438: Flowception: Temporally Expansive Flow Matching for Video Generation
Abstract page for arXiv paper 2511.05501: Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Cen...
Abstract page for arXiv paper 2510.12060: Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime