Hybrid GUI + MCP computer-use agents with reinforcement learning for tool use and multimodal context compression on OSWorld. Includes training, inference, and evaluation pipelines.
☆17Aug 5, 2026Updated 3 months ago
Alternatives and similar repositories for hybrid-routing-agent
Users that are interested in hybrid-routing-agent are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official code, data, and models for "Hint Tuning: Less Data Makes Better Reasoners"☆23Jul 8, 2026Updated 3 months ago
- Implementation of an efficient LLM architecture: the Pair-In / Pair-Out Model (PIPO)☆43Jun 10, 2026Updated 4 months ago
- A family of efficient edge language models in 100M~1B sizes.☆20Feb 14, 2025Updated last year
- An official implementation of "PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning" (EMNLP 2…☆13Nov 28, 2024Updated last year
- [EMNLP 2026 Findings] Official Repository of EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents☆12Mar 5, 2026Updated 8 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆11Nov 16, 2022Updated 3 years ago
- 风控算法,策略/模型☆16May 27, 2026Updated 5 months ago
- Position-independent caching for hybrid-attention LLM serving.☆20Jul 27, 2026Updated 3 months ago
- ☆10Jan 24, 2026Updated 9 months ago
- ☆15Apr 13, 2026Updated 6 months ago
- ☆12May 21, 2025Updated last year
- ☆10Jul 13, 2025Updated last year
- [ACM MM 2025 🔥 Oral] MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Uneth…☆16Mar 13, 2026Updated 7 months ago
- Official implementation of STaR-KV: training-free spatio-temporal KV cache compression for efficient GUI vision-language models.☆22Oct 17, 2026Updated 3 weeks 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.
- ☆12Jun 19, 2025Updated last year
- Discover feed url by RSS/Atom autodiscovery.☆15Nov 6, 2020Updated 6 years ago
- Code for EMNLP'24 paper - On Diversified Preferences of Large Language Model Alignment☆16Aug 6, 2024Updated 2 years ago
- Interaction Compass: Multi-Label Zero-Shot Learning of Human-Object Interactions via Spatial Relations @ ICCV21☆13Jul 15, 2022Updated 4 years ago
- An Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales☆16Jun 6, 2024Updated 2 years ago
- my poc☆16Oct 28, 2020Updated 6 years ago
- Agentic code retrieval benchmark for coding agents☆11Oct 27, 2026Updated last week
- 中山大学(SYSU)LMS 学习助手。全自动秒刷课、LLM 答题、自动跳转。提供油猴脚本和控制台版本。