Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022
The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning or fine-tuning. Training is reward-free and based on the Forward-Backward representation.
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
Code release for "Learning Video Representations from Large Language Models"
MoDem Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
Code and model release for the paper "Task-aware Retrieval with Instructions" by Asai et al.
A general purpose web app for connecting participants to engage in realtime conversations based on generated prompts.
code for "Semi-Discrete Normalizing Flows through Differentiable Tessellation"
code for "Neural Conservation Laws A Divergence-Free Perspective".
AutoCAT: Reinforcement Learning for Automated Exploration of Cache-Timing Attacks
Code and Models for "GeneCIS A Benchmark for General Conditional Image Similarity"
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
Code release for HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Code for the paper titled "CiT Curation in Training for Effective Vision-Language Data".
AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.
GPU-based Distributed Point Functions (DPF) and 2-server private information retrieval (PIR).
