johnny-wang16

awesome-bimanual-manipulation

Robot bimanual manipulation / dual-arm manipulation

ttt-lm-jax

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

robohive

A unified framework for robot learning

LLM101n

LLM101n: Let's build a Storyteller

rs-udpstreaming

DrEureka

Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024)

hato

🕊️ HATO: Learning Visuotactile Skills with Two Multifingered Hands

droid_policy_learning

DROID Policy Learning and Evaluation

low_cost_robot

ImageBind

ImageBind One Embedding Space to Bind Them All

scaling_on_scales

When do we not need larger vision models?

bias

professional-programming

A collection of learning resources for curious software engineers

gello_mechanical

weight-selection

D-TRAK

Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)

awesome

😎 Awesome lists about all kinds of interesting topics

Eureka

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

V1.0-Dexhand

The build files for the Dexhand

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

bridge_data_v2

bubogpt

BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

awesome-6d-object

Awesome work on object 6 DoF pose estimation

clip-retrieval

Easily compute clip embeddings and build a clip retrieval system with them

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

GenDataAttribution

Evaluating Data Attribution for Text-to-Image Models: a visual data attribution benchmark for evaluating and learning training image influences.

dreamsim

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight)

legged_gym

Isaac Gym Environments for Legged Robots

visual-tactile-synthesis

We synthesize synchronized visual appearance and tactile geometry given a sketch of objects and render the multimodal output on a surface haptic device called TanvasTouch.

Deep-RL-Notes

A collection of comprehensive notes on Deep Reinforcement Learning, customized for UC Berkeley's CS 285 (prev. CS 294-112)