OpenDCAI / DataFlexLinks
DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adjusting their mixing ratios.
☆30Updated last week
Alternatives and similar repositories for DataFlex
Users that are interested in DataFlex are comparing it to the libraries listed below
Sorting:
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆197Updated last month
- ☆60Updated 4 months ago
- The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"☆229Updated this week
- Official code repository for Sketch-of-Thought (SoT)☆129Updated 6 months ago
- Code for the paper "Coding Agents with Multimodal Browsing are Generalist Problem Solvers"☆89Updated last week
- MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning☆107Updated last week
- C^3-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking☆35Updated 4 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆101Updated 2 months ago
- Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"☆450Updated this week
- (ICCV 2025) OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation☆93Updated 4 months ago
- LongCodeZip: Compress Long Context for Code Language Models [ASE2025]☆116Updated 2 weeks ago
- MrlX: A Multi-Agent Reinforcement Learning Framework☆116Updated this week
- PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing☆20Updated 7 months ago
- LIMI: Less is More for Agency☆147Updated 3 weeks ago
- ☆87Updated last week
- [ICLR'25] ApolloMoE: Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts☆49Updated 11 months ago
- ☆92Updated last year
- Data Synthesis for Deep Research Based on Semi-Structured Data☆176Updated 3 weeks ago
- ☆125Updated 6 months ago
- Open-source examples and guides for building with the Qwen. Browse a collection of snippets, advanced techniques and walkthroughs.☆28Updated 11 months ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆109Updated 4 months ago
- ☆73Updated 5 months ago
- ☆29Updated 4 months ago
- An automated data pipeline scaling RL to pretraining levels☆67Updated 3 weeks ago
- ☆85Updated 7 months ago
- SSRL: Self-Search Reinforcement Learning☆149Updated 2 months ago
- The official repository of "R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Integration"☆120Updated 2 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆95Updated 6 months ago
- ☆73Updated 4 months ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆72Updated 4 months ago