Lists (1)
Stars
Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"
Minimalistic 4D-parallelism distributed training framework for education purpose
Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.
Configuration with Dataclasses+YAML+Argparse. Fork of Pyrallis
Unified Implementations of Offline Reinforcement Learning Algorithms
🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR25]
TART: A plug-and-play Transformer module for task-agnostic reasoning
Human-Level Competitive Pokémon via Scalable Offline Reinforcement Learning with Transformers
About Awesome things towards foundation agents. Papers / Repos / Blogs / ...
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
ByteCheckpoint: An Unified Checkpointing Library for LFMs
⚡⚡ Lightning Fast (~300TPS) Reinforcement Learning environment on latest Minecraft 🏝️
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
A benchmark to test and compare your pcg algorithm against each other
High quality implementations of imitation and inverse reinforcement learning algorithms
Official repository of the paper, PokeChamp: an Expert-level Minimax Language Agent for Competitive Pokemon.
NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"
Easily run PyTorch on multiple GPUs & machines