ltlhuuu / PSECLinks
[ICLR 2025] The offical implementation of "PSEC: Skill Expansion and Composition in Parameter Space", a new framework designed to facilitate efficient and flexible skill expansion and composition, iteratively evolve the agents' capabilities and efficiently address new challenges
☆62Updated 10 months ago
Alternatives and similar repositories for PSEC
Users that are interested in PSEC are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.☆101Updated 3 weeks ago
- EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models☆53Updated 3 weeks ago
- [ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.☆249Updated 2 months ago
- [ICCV 2025] RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints☆100Updated 4 months ago
- Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning☆26Updated 6 months ago
- [ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"☆82Updated 7 months ago
- 🦾 A Dual-System VLA with System2 Thinking☆129Updated 4 months ago
- ☆217Updated 4 months ago
- MM-ACT: Learn from Multimodal Parallel Generation to Act☆89Updated last week
- Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.☆363Updated 2 months ago
- LIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark☆147Updated 3 weeks ago
- [ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos☆158Updated 3 months ago
- [NeurIPS 2025] DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge☆273Updated this week
- GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization☆154Updated 9 months ago
- ☆27Updated last month
- [ICCV 2025] Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation.☆50Updated 4 months ago
- [NeurIPS 2025] VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning☆65Updated 3 weeks ago
- Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"☆114Updated last month
- A collection of vision-language-action model post-training methods.☆113Updated 2 months ago
- Embodied Intelligence in Endovascular Robot Navigation -- 血管介入手术机器人具身导航☆21Updated 3 weeks ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆190Updated 6 months ago
- InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy☆330Updated last week
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆162Updated 3 months ago
- Official code of paper "DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution"☆122Updated 10 months ago
- ICCV2025☆145Updated last month
- [NeurIPS 2025] VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulation☆58Updated 3 months ago
- Unified Vision-Language-Action Model☆257Updated 2 months ago
- [ICML 2024] The offical implementation of A2PR, a simple way to achieve SOTA in offline reinforcement learning with an adaptive advantage…☆34Updated last year
- Official code for "Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation"☆115Updated 4 months ago
- [AAMAS'26] xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing☆21Updated this week