yilundu's repositories
cross_attention_renderer
CVPR 2023: Learning to Render Novel Views from Wide-Baseline Stereo Pairs
reduce_reuse_recycle
ICML 2023: Reduce, Reuse, Recycle: Composing Energy-Based Diffusion Models with MCMC
improved_contrastive_divergence
[ICML'21] Improved Contrastive Divergence Training of Energy Based Models
ebm_compositionality
[NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models
irem_code_release
ICML 2022: Learning Iterative Reasoning through Energy Minimization
DQN-DDQN-on-Space-Invaders
Implementation of Double Deep Q Networks and Dueling Q Networks using Keras on Space Invaders using OpenAI Gym. Code can be easily generalized to other Atari games.
imagination_augmented_agents
Replicating Imagination-Augmented Agents for Deep Reinforcement Learning
task_agnostic_dynamics_prior
Code Release for Task Agnostic Dynamics Priors for Deep Reinforcement Learning
model_based_planning_ebm
CORL 2019: Model Based Planning with Energy Based Models
style-based-gan-pytorch
Implementation A Style-Based Generator Architecture for Generative Adversarial Networks in PyTorch
awesome-NeRF
A curated list of awesome neural radiance fields papers
colorization
Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
habitat-sim
A flexible, high-performance 3D simulator for Embodied AI research.
kubric
A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.
Recurrent-Interaction-Network
Pytorch implementation of Recurrent Interaction Networks, from "Occlusion resistant learning of intuitive physics from videos"
shape2prog
Learning to Infer and Execute 3D Shape Programs (ICLR 2019)
visual_mpc
Visual MPC implementation running on Rethink Sawyer Robot