mihirp1998

trl

Train transformer language models with reinforcement learning.

Adversarial-Inverse-Graphics-Networks-for-Faces

AlignProp

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

Diffusion-TTA

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

Disentangling-3D-Prototypical-Nets

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.

EmbLang

Embodied Language Grounding With 3D Visual Feature Representations

Navigation-Deep-RL

This is a rep for navigating in unity environment using deep q learning network in pytroch

ProbabilisticNeuralProgrammedNetwork_Tensorflow

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

Slot-TTA

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

VADER

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.

mihirp1998/AlignProp

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

mihirp1998/VADER

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.

mihirp1998/Diffusion-TTA

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

mihirp1998/Slot-TTA

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

mihirp1998/cmu-vision.github.io

mihirp1998/ComplexAutoEncoder

Code for the paper: Complex-Valued Autoencoders for Object Discovery

mihirp1998/DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

mihirp1998/Depth-Adaptive-Visual-Tracking-tf

This is an unofficial implementation of the Paper "Depth-Adaptive Computational Policies for Efficient Visual Tracking" By Chris Ying, Katerina Fragkiadaki

mihirp1998/dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

mihirp1998/DiT

mihirp1998/dotfiles

mihirp1998/grok

mihirp1998/hora

In-Hand Object Rotation via Rapid Motor Adaptation (CoRL 2022)

mihirp1998/mae_aug

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

mihirp1998/Maskgit-pytorch

mihirp1998/multiobjective_symbolic_regression

This is a Python library that implements a Multi-objective Symbolic Regression algorithm. It can be used as a Machine Learning algorithm to create predictive models in the form of mathematical expressions.

mihirp1998/OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

mihirp1998/project_template

mihirp1998/pymunk

Pymunk is a easy-to-use pythonic 2d physics library that can be used whenever you need 2d rigid body physics from Python

mihirp1998/retrieval-latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

mihirp1998/rlbench

mihirp1998/RLBench-1

A large-scale benchmark and learning environment.

mihirp1998/SlotCon

(NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping

mihirp1998/stable-dreamfusion

A working implementation of text-to-3D dreamfusion, powered by stable diffusion.

mihirp1998/time-change

mihirp1998/tmp

mihirp1998/tmp1

mihirp1998/tmp3

mihirp1998/toy-diffusion

A toy implementation of a diffusion model for low-dimensional data

mihirp1998/trl

Train transformer language models with reinforcement learning.