The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL Paper • 2606.19162 • Published 9 days ago • 20
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction Paper • 2606.18558 • Published 9 days ago • 50
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL Paper • 2606.19162 • Published 9 days ago • 20
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL Paper • 2606.19162 • Published 9 days ago • 20
RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space Paper • 2606.14700 • Published 14 days ago • 18
view article Article We’re open-sourcing our text-to-image model and the process behind it Photoroom • Nov 12, 2025 • 100
GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation Paper • 2512.16853 • Published Dec 18, 2025 • 1
Inference-time Physics Alignment of Video Generative Models with Latent World Models Paper • 2601.10553 • Published Jan 15 • 13
Inference-time Physics Alignment of Video Generative Models with Latent World Models Paper • 2601.10553 • Published Jan 15 • 13