corl-team repositories

19 repositories

kronsae
Public
Jupyter Notebook
•
Apache License 2.0
•0•2•0•0•Updated Oct 14, 2026Oct 14, 2026
qantara
Public
Qantara: one JEPA world-model checkpoint that serves latent planning, behaviour cloning, and video-inverse control from pixels.
pytorch planning model-based-rl
pytorch planning model-based-rl world-models embodied-ai jepa
Python
•
MIT License
•1•13•0•0•Updated Oct 14, 2026Oct 14, 2026
namvis
Public
NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis (NeurIPS 2026)
pytorch generative-model autoregressive
pytorch generative-model autoregressive 3d-generation novel-view-synthesis sparse-view next-scale-prediction visual-autoregressive neurips-2026 multi-view-synthesis
Python
•
MIT License
•0•10•1•0•Updated Oct 8, 2026Oct 8, 2026
rank-then-act
Public
Official implementation of the paper "Rank-Then-Act: Reward-Free Control from Frame-Order Progress"
reinforcement-learning pytorch representation-learning
reinforcement-learning pytorch representation-learning robot-learning embodied-ai
Python
•
MIT License
•0•6•0•0•Updated Sep 15, 2026Sep 15, 2026
nedreamer
Public
Official implementation of the paper "Next Embedding Prediction Makes World Models Stronger"
pytorch representation-learning model-based-rl
pytorch representation-learning model-based-rl world-models embodied-ai
Python
•
MIT License
•2•41•1•0•Updated Aug 24, 2026Aug 24, 2026
VL-DAC
Public
Official implementation of the paper "Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success"
reinforcement-learning pytorch vla
reinforcement-learning pytorch vla embodied-ai vision-language-model
Python
•
MIT License
•0•14•1•0•Updated Aug 24, 2026Aug 24, 2026
netherite-prime-agent
Public
Letting an LLM play netherite (Minecraft 1.11.2 rewritten in C) through Prime Agent
Python
•
MIT License
•1•2•0•0•Updated Aug 7, 2026Aug 7, 2026
counting_manifolds
Public
Code for the reproduction of counting manifolds
Python
•
Apache License 2.0
•2•16•0•0•Updated Feb 26, 2026Feb 26, 2026
steering-reasoning
Public
Official implementation of "Steering LLM Reasoning Through Bias-Only Adaptation" and "Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning vi…
Python
•
Apache License 2.0
•5•57•2•0•Updated Oct 7, 2025Oct 7, 2025
flexsae
Public
Official Triton kernels for TopK and HierarchicalTopK Sparse Autoencoder decoders.
triton emnlp sae
triton emnlp sae interpretability sparse-autoencoder llm emnlp2025
Python
•
Apache License 2.0
•1•29•0•0•Updated Sep 29, 2025Sep 29, 2025
lime
Public
Official implementation of the paper "You Do Not Fully Utilize Transformer's Representation Capacity"
language transformer llm
language transformer llm llm-training
Python
•
Apache License 2.0
•1•32•1•0•Updated May 28, 2025May 28, 2025
verl-loras
Public
verl: Volcano Engine Reinforcement Learning for LLMs
Python
•
Apache License 2.0
•4.8k•0•0•0•Updated May 7, 2025May 7, 2025
rebased
Public
Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"
nlp pytorch transformer
nlp pytorch transformer in-context-learning acl2024
Python
•
Apache License 2.0
•3•168•4•0•Updated Jan 16, 2025Jan 16, 2025
ad-eps
Public
Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"
reinforcement-learning meta-rl in-context
reinforcement-learning meta-rl in-context in-context-reinforcement-learning algorithm-distillation
Python
•2•35•0•0•Updated Sep 18, 2024Sep 18, 2024
sdde
Public
[IEEE ICIP 2024] Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
Python
•
Apache License 2.0
•1•8•0•0•Updated Jun 19, 2024Jun 19, 2024
toy-meta-gym
Public
Toy meta-RL environments for testing algorithms implementations
reinforcement-learning meta-rl in-context-reinforcement-learning
reinforcement-learning meta-rl in-context-reinforcement-learning
Python
•
Apache License 2.0
•0•10•0•1•Updated Feb 21, 2024Feb 21, 2024
headless-ad
Public
Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"
reinforcement-learning meta-rl in-context-learning
reinforcement-learning meta-rl in-context-learning in-context-reinforcement-learning algorithm-distillation
Python
•5•92•0•0•Updated Feb 11, 2024Feb 11, 2024
CORL
Public
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL,…
Python
•
Apache License 2.0
•177•663•4•1•Updated Feb 10, 2024Feb 10, 2024
katakomba
Public
Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)
Python
•
Other
•3•43•0•0•Updated Aug 22, 2023Aug 22, 2023

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.

Navigation Menu

corl-team

All

19 repositories

kronsae

qantara

namvis

rank-then-act

nedreamer

VL-DAC

netherite-prime-agent

counting_manifolds

steering-reasoning

flexsae

lime

verl-loras

rebased

ad-eps

sdde

toy-meta-gym

headless-ad

CORL

katakomba

Repositories list

19 repositories