Language Breakdown
Lines of code distribution across 59 owned repositories
T-Shaped Developer
T-shapedDeep in Python with broad versatility
Collaboration Network
Global Impact visualization
Repos
129
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Not following anyone yet.
Top Repositories
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 (PPO) for finetuning Stable Diffusion
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 reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.
Diffusion-TTA improves pre-trained discriminative models such as image classifiers or segmentors using pre-trained generative models.
Implementation of Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
Slot-TTA shows that test-time adaptation using slot-centric models can improve image segmentation on out-of-distribution examples.
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 few-shot concept classification.
Code for "Probabilistic Neural Programmed Networks for Scene Generation.", Deng et al, NIPS 2018. This Code Base is ported Tensorflow 2.0 version of the official Pytorch Implementation
Embodied Language Grounding With 3D Visual Feature Representations
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Open Source Impact
Contributions to external projects
