Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
☆20Aug 17, 2026Updated 2 months ago
Alternatives and similar repositories for Pion
Users that are interested in Pion are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- RL²-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models☆41Aug 31, 2026Updated last month
- ☆29Aug 25, 2026Updated last month
- VLAC-Cut is a video-language progress estimation model for robotic manipulation.☆29Sep 16, 2026Updated last month
- ☆43May 18, 2026Updated 5 months ago
- FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLAs Inference☆59Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation☆155Sep 20, 2026Updated last month
- Unofficial OpenPI extension experiment to build a more complete OpenPI-style VLA engineering stack: pi0.5 semantics, RTC, pi0.6 RECAP/MEM…☆49Jul 8, 2026Updated 3 months ago
- The official implementation of Assistron: Bayesian Shared Autonomy with Off-the-shelf Vision-Language-Action Models☆60Jun 23, 2026Updated 4 months ago
- FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space☆88Sep 22, 2026Updated last month
- ☆36Aug 30, 2026Updated last month
- ☆46Aug 28, 2026Updated last month
- Official Release of "Mixture of Horizons in Action Chunking", ICML 2026☆67May 4, 2026Updated 5 months ago
- A curated list and taxonomy of test-time robot learning: RL post-training, policy steering, test-time adaptation and training, test-time …☆27Sep 30, 2026Updated 3 weeks ago
- Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon ro…☆94Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Official repository of "Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts" [ECCV'26]☆25Aug 3, 2026Updated 2 months ago
- RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning — project page☆20Oct 8, 2026Updated 2 weeks ago
- [ICML 2026] Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models☆105May 18, 2026Updated 5 months ago
- [CVPR 2026] Official Implementation for Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Effi…☆35Jul 16, 2026Updated 3 months ago
- Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models☆16Apr 23, 2026Updated 6 months ago
- Value-guided action selection and self-improvement for frozen behaviour-cloning policies☆71Aug 24, 2026Updated last month
- Kinetix simulation for Legato: Learning Native Continuation for Action Chunking Flow Policies (RSS 2026)☆35Jun 3, 2026Updated 4 months ago
- Learning & Acquisition of Behaviors Suite. Microservice-driven robotics data orchestration platform that coordinates actuators, sensors, …☆41Sep 10, 2026Updated last month
- Implementation of the paper "Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning" (htt…☆51Sep 10, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing☆115Jul 24, 2026Updated 2 months ago
- Code and diagnostics for the manipulation benchmark audit paper.☆19Oct 13, 2026Updated last week
- VLA-GSE: Boosting Parameter Efficient Finetuning in VLA with Generalized and Specialized Experts☆21Jul 11, 2026Updated 3 months ago
- [CoRL2026] MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model☆19Sep 7, 2026Updated last month
- A Controlled Laboratory for Vision-Language-Action Policy Research☆36Jul 27, 2026Updated 2 months ago
- Official implementation of "SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation"☆28Aug 13, 2026Updated 2 months ago
- World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty☆26Sep 1, 2026Updated last month
- [ECCV2026] 360CityArena☆30Updated this week
- An extended version of robotwin benchmark☆15Jul 29, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- FASTER: Value-Guided Sampling for Fast RL☆32Jun 30, 2026Updated 3 months ago
- Official repo for paper "HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies"☆36Sep 5, 2026Updated last month
- MC-Sparse: Deconstructing and Closing the Dense–Sparse Attention Gap in Diffusion Transformers.☆46Oct 6, 2026Updated 2 weeks ago
- ☆65Oct 14, 2026Updated last week
- Agents for robot physical reasoning☆27Oct 7, 2026Updated 2 weeks ago
- ☆83Sep 7, 2026Updated last month
- Official implementation of Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics☆22Mar 12, 2026Updated 7 months ago