论文与新闻
August 17, 2026 · View on GitHub
本页面汇总与 EasyDistill 项目及其衍生模型、数据集相关的学术论文与技术文章。
学术论文
| 论文 | 作者 | 发表 | 链接 |
|---|---|---|---|
| EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models | Chengyu Wang, Junbing Yan, Wenrui Cai, Yuanhao Yue, Jun Huang | EMNLP 2025 | arXiv |
| Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards | Yuanjie Lyu, Chengyu Wang, Lei Shen, Jun Huang, Tong Xu | ACL 2026 | arXiv |
| AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use | Yuanjie Lyu, Chengyu Wang, Haonan Zheng, Yuanhao Yue, Junbing Yan, Ming Wang, Jun Huang | ACL 2026 | arXiv |
| Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations | Wenrui Cai, Chengyu Wang, Junbing Yan, Jun Huang, Xiangzhong Fang | ACL 2026 | arXiv |
| Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series | Wenrui Cai, Chengyu Wang, Junbing Yan, Jun Huang, Xiangzhong Fang | EMNLP 2025 | arXiv |
| Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment | Wenrui Cai, Chengyu Wang, Junbing Yan, Jun Huang, Xiangzhong Fang | EMNLP 2025 | arXiv |
| DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models | Chengyu Wang, Junbing Yan, Yuanhao Yue, Jun Huang | ACL 2025 | arXiv |
| Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud | Yuanhao Yue, Chengyu Wang, Jun Huang, Peng Wang | COLING 2025 | arXiv |
| Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning | Yuanhao Yue, Chengyu Wang, Jun Huang, Peng Wang | EMNLP 2024 | arXiv |
技术文章
| 标题 | 来源 | 语言 | 链接 |
|---|---|---|---|
| 面向 Interleaved Thinking 的大模型 Agent 蒸馏实践 | 知乎专栏 | 中文 | Link |
| OmniThoughtV：面向多模态深度思考的高质量数据蒸馏 | 微信公众号 | 中文 | Link |
| 基于模型蒸馏的大模型文案生成最佳实践 | 阿里云开发者社区 | 中文 | Link |
| DistilQwen-ThoughtY：通过变长思维链蒸馏，全面提升模型推理能力！ | 阿里云开发者社区 | 中文 | Link |
| DistilQwen-ThoughtX：变长思维链推理模型，能力超越DeepSeek蒸馏模型 | 阿里云开发者社区 | 中文 | Link |
| 阿里云人工智能平台 PAI 开源 EasyDistill 框架助力大语言模型轻松瘦身 | 阿里云开发者社区 | 中文 | Link |
| 人工智能平台 PAI DistilQwen2.5-DS3-0324发布：知识蒸馏+快思考=更高效解决推理难题 | 阿里云开发者社区 | 中文 | Link |
| DistilQwen2.5-R1发布：知识蒸馏助推小模型深度思考 | 阿里云开发者社区 | 中文 | Link |
| DistilQwen2.5发布：通义千问蒸馏小模型再升级 | 阿里云开发者社区 | 中文 | Link |
| DistilQwen2：通义千问大模型的知识蒸馏实践 | 阿里云开发者社区 | 中文 | Link |
| 基于多轮课程学习的大语言模型蒸馏算法TAPIR | 阿里云开发者社区 | 中文 | Link |