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 282 10

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 270 15

3. 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 92 4

4. Diffusion-TTA Diffusion-TTA Public

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

   Python 72 5

5. Slot-TTA Slot-TTA Public

   Slot-TTA shows that test-time adaptation using slot-centric models can improve image segmentation on out-of-distribution examples.

   Python 26 3

6. huggingface/trl huggingface/trl Public

   Train transformer language models with reinforcement learning.

   Python 13.5k 1.8k