MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
☆112Feb 2, 2026Updated 3 weeks ago
Alternatives and similar repositories for MegaScience
Users that are interested in MegaScience are comparing it to the libraries listed below
Sorting:
- Reproducible and flexible LLM evaluations for scientific reasoning.☆26Jul 23, 2025Updated 7 months ago
- Official repository of paper "Context-DPO: Aligning Language Models for Context-Faithfulness"☆21Feb 17, 2025Updated last year
- ☆31Sep 12, 2025Updated 5 months ago
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆81Dec 25, 2025Updated 2 months ago
- ☆25Aug 19, 2025Updated 6 months ago
- ☆46Jun 24, 2025Updated 8 months ago
- [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆15Feb 9, 2026Updated 2 weeks ago
- An interactive thinking and deep reasoning model. It provides a cognitive reasoning paradigm for complex multi-hop problems.☆79Nov 14, 2025Updated 3 months ago
- Mixture-of-Basis-Experts for Compressing MoE-based LLMs☆29Dec 24, 2025Updated 2 months ago
- More reliable Video Understanding Evaluation☆14Sep 23, 2025Updated 5 months ago
- [COLING 2025] Official repo of paper: "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jail…☆12Jul 26, 2024Updated last year
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆159Jun 26, 2025Updated 8 months ago
- Sotopia-RL: Reward Design for Social Intelligence☆46Jan 29, 2026Updated last month
- Python binding for Jagger(C++ implementation of Pattern-based Japanese Morphological Analyzer)☆12Dec 16, 2025Updated 2 months ago
- ☆16Mar 4, 2024Updated last year
- ☆23May 21, 2025Updated 9 months ago
- Codebase for paper ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools☆26Nov 3, 2025Updated 3 months ago
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning☆62Oct 24, 2025Updated 4 months ago
- A comprehensive and efficient long-context model evaluation framework☆31Feb 8, 2026Updated 2 weeks ago
- From Word to World: Can Large Language Models be Implicit Text-based World Models?☆46Dec 25, 2025Updated 2 months ago
- [ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents☆33Feb 1, 2026Updated 3 weeks ago
- ☆99Aug 8, 2025Updated 6 months ago
- [ICLR 2026] Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"☆121Feb 2, 2026Updated 3 weeks ago
- [ACL 2025 (Findings)] DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling☆22Dec 16, 2024Updated last year
- PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration☆41Jan 7, 2026Updated last month
- ♾️🦙 Let's DIY infinite TinyLlamas in your room!☆16May 6, 2024Updated last year
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆29Oct 9, 2025Updated 4 months ago
- ☆76Jan 24, 2025Updated last year
- [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆53Sep 29, 2025Updated 5 months ago
- Data Synthesis for Deep Research Based on Semi-Structured Data☆199Dec 18, 2025Updated 2 months ago
- ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]☆20Aug 21, 2025Updated 6 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆221Nov 27, 2025Updated 3 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆51Jul 15, 2025Updated 7 months ago
- Source code of our EMNLP 2024 paper "FactAlign: Long-form Factuality Alignment of Large Language Models"☆19Oct 3, 2024Updated last year
- [ACM MM25] LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models☆23Mar 29, 2025Updated 10 months ago
- Code and data for paper "Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation".☆23Oct 22, 2025Updated 4 months ago
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆26Aug 9, 2025Updated 6 months ago
- Synthetic data generation for evaluating LLM symbolic and logic reasoning☆22Mar 20, 2025Updated 11 months ago
- Code, Data and Model for Paper "Learning from Peers in Reasoning Models"☆27May 13, 2025Updated 9 months ago