PinnedLoading

1. AlignPropAlignPropPublic

   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 277 10

2. VADERVADERPublic

   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 247 15

3. Diffusion-TTADiffusion-TTAPublic

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

   Python 68 5

4. Slot-TTASlot-TTAPublic

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

   Python 26 3

5. Disentangling-3D-Prototypical-NetsDisentangling-3D-Prototypical-NetsPublic

   We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and …

   Python 11

6. huggingface/trlhuggingface/trlPublic

   Train transformer language models with reinforcement learning.

   Python 12.6k 1.7k