modelscope / mcp-centralLinks
Collection of model-centric MCP servers
☆23Updated 3 months ago
Alternatives and similar repositories for mcp-central
Users that are interested in mcp-central are comparing it to the libraries listed below
Sorting:
- ☆129Updated 2 weeks ago
- ☆292Updated 3 months ago
- a toolkit on knowledge distillation for large language models☆153Updated this week
- ☆81Updated 5 months ago
- 最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。☆44Updated 7 months ago
- Official implementation for "ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization"☆83Updated 3 months ago
- Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"☆145Updated 3 months ago
- Deep Reasoning Translation (DRT) Project☆231Updated 2 weeks ago
- ☆48Updated last week
- PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, constraining p…☆25Updated last week
- Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414☆336Updated 3 weeks ago
- IKEA: Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent☆64Updated 4 months ago
- Efficient Agent Training for Computer Use☆131Updated 2 weeks ago
- MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.☆314Updated this week
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 4 months ago
- ☆49Updated last year
- Code for Paper: Test-Time Reinforcement Learning for GUI Grounding via Region Consistency☆42Updated last month
- ☆95Updated 9 months ago
- ☆165Updated 4 months ago
- ☆89Updated 4 months ago
- The code for paper: Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search☆57Updated 2 months ago
- 代码大模型 预训练&微调&DPO 数据处理 业界处理pipeline sota☆44Updated last year
- This is the code repo for our paper "Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts".☆39Updated last month
- ☆54Updated last year
- ☆59Updated 10 months ago
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆230Updated last month
- FlexRAG: A RAG Framework for Information Retrieval and Generation.☆221Updated 3 months ago
- ☆33Updated 3 months ago
- Unleashing the Power of Cognitive Dynamics on Large Language Models☆63Updated 11 months ago
- Agentic Foundation Platform☆471Updated this week