Scaling Active Perception for Robots across Model, Data, and Hardware
☆18Sep 19, 2026Updated last month
Alternatives and similar repositories for ActiveScale
Users that are interested in ActiveScale are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆24Oct 6, 2026Updated last month
- Official code of Discrete Forcing☆16Oct 4, 2026Updated last month
- ☆51May 12, 2026Updated 6 months ago
- Official code of UniWAM: Unified World-Action Model☆140Oct 12, 2026Updated last month
- Build your own Claude Code-like agent from scratch, step by step, with AI assistance.☆13Mar 7, 2026Updated 8 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Official implementation of FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment☆58Mar 24, 2026Updated 7 months ago
- ActionCodec: What Makes for Good Action Tokenizers☆81Mar 1, 2026Updated 8 months ago
- Official implementation of Video Prediction Policy 2: Predict Better, Act Better☆373Oct 19, 2026Updated 3 weeks ago
- [IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Policies☆566Nov 3, 2026Updated last week
- [RSS 2026 Finalist] Ordered Action Tokenization☆120Jul 27, 2026Updated 3 months ago
- ☆32Oct 20, 2026Updated 3 weeks ago
- RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark☆163Nov 1, 2026Updated last week
- ☆13Sep 2, 2023Updated 3 years ago
- [ACM MM'26 Oral] MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation☆70May 14, 2026Updated 5 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- GeRM: A Generalist Robotic Model with Mixture-of-Experts for Quadruped Robot https://songwxuan.github.io/GeRM/☆38Apr 29, 2025Updated last year
- 空間智能的跨 embodiment 手冊 —— 把 SLAM / VIO / 3D 表徵 / 感測器堆疊 / 部署坑 在 機械臂 / 無人機 / 自駕 / 人形 / 水下 之間橫向比較，底層共用 3DGS / VGGT / depth foundation。照見三冊 per…☆38Updated this week
- A Controlled Laboratory for Vision-Language-Action Policy Research☆37Jul 27, 2026Updated 3 months ago
- ☆10May 26, 2022Updated 4 years ago
- Anchor-Align (arXiv:2607.13429): VLA finetuning that prevents behavior cloning from erasing pretrained VLM representations (catastrophic …☆43Oct 24, 2026Updated 2 weeks ago
- ☆17Oct 20, 2026Updated 3 weeks ago
- Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".☆1,196Updated this week
- The official implementation of VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training☆35Jun 26, 2026Updated 4 months ago
- Continuous Conflict-Based Search (CCBS) implementation in Python☆12Nov 28, 2023Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆22Oct 29, 2026Updated 2 weeks ago
- ☆18Nov 5, 2026Updated last week
- ☆12Oct 4, 2026Updated last month
- 主要用于清洗从高德地图搜索得到的地铁线路数据并生成SHP文件和GeoJSON文件，涵盖了高德坐标系、百度坐标系和WGS1984坐标系三种类型的坐标点数据，方便在不同地图平台上使用。☆13Sep 28, 2024Updated 2 years ago
- official code of CCD, a novel decoding method for DLMs☆14Dec 4, 2025Updated 11 months ago
- RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation☆103Jul 16, 2026Updated 3 months ago
- ☆12Sep 22, 2026Updated last month
- World Action Model, VLA failure detection/correction, Efficient VLA☆26Updated this week
- The paper list of the survey "The Past Frames the Future: Memory Mechanisms for Autoregressive Video Generation"☆99Oct 18, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official code release for EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors. https://eigendexplore.githu…☆60Oct 11, 2026Updated last month
- Towards Long-Horizon Vision-Language-Action System: Reasoning, Acting and Memory☆12Jun 30, 2025Updated last year
- ☆59Aug 31, 2026Updated 2 months ago
- DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation☆28Sep 30, 2026Updated last month
- Official code for StarVLA-alpha: a simple, direct, high-performing VLA baseline.☆12Aug 5, 2026Updated 3 months ago
- Precedence constrained multi-agent task assignment and path finding☆17Dec 26, 2023Updated 2 years ago
- LLaVA-VLA: A Simple Yet Powerful Vision-Language-Action Model [ICRA 2026]☆214Mar 12, 2026Updated 8 months ago
Are these results useful?