Pinned Loading

1. AlignProp AlignProp Public

   AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods…

   Python 329 11

2. VADER VADER Public

   Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various r…

   Python 318 15

3. Sim2Reason/Sim2Reason Sim2Reason/Sim2Reason Public

   Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators. We present a method for turning physics simulators into scalable generators of question–answer pairs for impro…

   Python 178 24

4. alexanderswerdlow/unidisc alexanderswerdlow/unidisc Public

   UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, and inpainting.

   Python 144 6

5. wmn-231314/diffusion-data-constraint wmn-231314/diffusion-data-constraint Public

   Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion models are significantly more data-efficient than standard left…

   Python 128 6

6. Diffusion-TTA Diffusion-TTA Public

   Diffusion-TTA improves pre-trained discriminative models such as image classifiers or segmentors using pre-trained generative models.

   Python 80 5