CognitiveAISystems repositories

25 repositories

ResearcherOS
Public
ResearchOS is an open-source platform for organizing AI-assisted research.
Python
•2•17•5•2•Updated Oct 12, 2026Oct 12, 2026
DMM
Public
Python
•
MIT License
•1•5•0•0•Updated Oct 3, 2026Oct 3, 2026
FocusGraph
Public
Python
•0•1•0•0•Updated Oct 1, 2026Oct 1, 2026
LC-MAPF
Public
Local communication for scalable multi-agent pathfinding
Python
•
MIT License
•1•10•0•0•Updated Sep 27, 2026Sep 27, 2026
VLA-Grounder
Public
VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
Python
•
Apache License 2.0
•0•3•0•0•Updated Sep 22, 2026Sep 22, 2026
muVLA
Public
https://arxiv.org/abs/2606.12497
Python
•
Other
•1•12•1•0•Updated Aug 12, 2026Aug 12, 2026
Act2Answer
Public
🔥[EMNLP 2026] Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Python
•
MIT License
•0•14•1•0•Updated Jul 1, 2026Jul 1, 2026
kage-bench
Public
🔥 [ICML 2026] KAGE-Bench: pure JAX 2D platformer RL benchmark for visual OOD generalization. Massively-parallel (vmap/JIT) RGB env with YAML-configurable visual…
benchmark rl ood
benchmark rl ood generalization ppo jax rl-environment ood-generalization visual-generalization
Python
•
MIT License
•0•13•0•0•Updated Jul 1, 2026Jul 1, 2026
MIKASA-Robo
Public
🔥 [ICLR 2026] Benchmark for robotic tabletop manipulation memory-intensive tasks
benchmark reinforcement-learning memory
benchmark reinforcement-learning memory rl vla pomdp maniskill visual-language-action-models
Python
•
MIT License
•17•140•4•2•Updated Jun 30, 2026Jun 30, 2026
OVSegDT
Public
OVSegDT, a lightweight transformer policy to solve Open-vocabulary Object Goal Navigation
Python
•3•19•2•0•Updated May 25, 2026May 25, 2026
MAPF-GPT
Public
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced b…
transformers mapf pogema
transformers mapf pogema aaai-2025
C++
•
MIT License
•25•135•0•0•Updated Apr 23, 2026Apr 23, 2026
SuperIgor
Public
Python
•
Apache License 2.0
•0•2•0•0•Updated Apr 20, 2026Apr 20, 2026
transformers-mu-openvla-oft
Public
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python
•
Apache License 2.0
•35k•0•0•0•Updated Apr 16, 2026Apr 16, 2026
ReSCALE
Public
Python
•
Apache License 2.0
•1•5•0•0•Updated Mar 26, 2026Mar 26, 2026
3DGraphLLM
Public
[ICCV 2025] 3DGraphLLM is a model that uses a 3D scene graph and an LLM to perform 3D vision-language tasks.
3d-scene-graph 3d-scene-understanding 3d-visual-grounding
3d-scene-graph 3d-scene-understanding 3d-visual-grounding llms
Python
•
MIT License
•8•127•0•0•Updated Mar 23, 2026Mar 23, 2026
Dynamic-Neural-Potential-Field
Public
Approach where the repulsive potential in an MPC pipeline is estimated by a neural model.
C
•
Apache License 2.0
•1•28•1•0•Updated Mar 5, 2026Mar 5, 2026
BlindVLA
Public
🔥[AAMAS 2026 Oral] Don’t Blind Your VLA: Aligning Visual Representations for OOD Generalization. https://blind-vla-paper.github.io
robotics alignment representation-learning
robotics alignment representation-learning ood vla generalization maniskill
Python
•
MIT License
•3•70•1•0•Updated Jan 25, 2026Jan 25, 2026
RATE
Public
🔥 [ICLR 2026] Official implementation of Recurrent Action Transformer with Memory, an offline RL agent with memory mechanisms. https://sites.google.com/view/rat…
reinforcement-learning deep-learning memory
reinforcement-learning deep-learning memory transformer rate rl memory-rl long-context recurrent-action-transformer-with-memory
Python
•
MIT License
•3•26•1•0•Updated Nov 23, 2025Nov 23, 2025
learn-to-follow
Public
[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a …
grid reinforcement-learning pathfinding
grid reinforcement-learning pathfinding mapf lifelong aaai-2024 pogema
0•6•0•0•Updated Jul 7, 2025Jul 7, 2025
mats-lp
Public
[AAAI-2024] MATS-LP addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed approach utilizes a combination of Monte C…
grid multi-agent mcts
grid multi-agent mcts mapf lifelong aaai-2024 pogema
1•2•0•0•Updated Jul 7, 2025Jul 7, 2025
pogema-benchmark
Public
This is an umbrella repository that contains links and information about all the tools and algorithms related to the POGEMA Benchmark.
1•2•0•0•Updated Jul 7, 2025Jul 7, 2025
pogema-toolbox
Public
The POGEMA Toolbox is a comprehensive framework designed to facilitate the testing of learning-based approaches within the POGEMA environment. This toolbox offe…
grid pathfinding mapf
grid pathfinding mapf pogema
1•4•0•0•Updated Jul 7, 2025Jul 7, 2025
pogema
Public
POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tun…
reinforcement-learning simulation pathfinding
reinforcement-learning simulation pathfinding mapf marl decentralized-mapf
9•46•0•0•Updated Jul 7, 2025Jul 7, 2025
SegDT
Public
Segmenting Decision Transformer (SegDT) for Semantic Object Goal-Reaching task
Python
•0•7•0•0•Updated Jun 4, 2025Jun 4, 2025
MIKASA-Base
Public
Unified Benchmark for Memory-Intensive Tasks
python benchmark reinforcement-learning
python benchmark reinforcement-learning memory rl pomdp enviroments
Python
•
MIT License
•1•7•0•0•Updated Feb 24, 2025Feb 24, 2025

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

Navigation Menu

CognitiveAISystems

All

25 repositories

ResearcherOS

DMM

FocusGraph

LC-MAPF

VLA-Grounder

muVLA

Act2Answer

kage-bench

MIKASA-Robo

OVSegDT

MAPF-GPT

SuperIgor

transformers-mu-openvla-oft

ReSCALE

3DGraphLLM

Dynamic-Neural-Potential-Field

BlindVLA

RATE

learn-to-follow

mats-lp

pogema-benchmark

pogema-toolbox

pogema

SegDT

MIKASA-Base

Repositories list

25 repositories