AI前沿:从数学推理到记忆注入 episode artwork

EPISODE · May 2, 2025 · 9 MIN

AI前沿:从数学推理到记忆注入

from AI可可AI生活

本期播客精华汇总 Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in MathPhi-4-Mini-Reasoning:探索小型数学推理语言模型的极限通过四阶段训练(大规模蒸馏、微调、偏好优化、强化学习),仅38亿参数的Phi-4-Mini-Reasoning在数学推理上超越70亿-80亿参数模型,揭示小模型需“量体裁衣”的训练策略,反直觉地发现朴素高质量数据可能有害。 ParamΔ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost直接权重混合的 ParamΔ:零成本训练后的大型语言模型ParamΔ通过简单权重差值加法,将后训练能力零成本迁移到新基座模型,性能达官方版的95%,为开源社区提供高效模型更新方案,揭示参数空间的代数结构潜力。 Model Connectomes: A Generational Approach to Data-Efficient Language Models模型连接组:一种面向数据高效的语言模型的方法受生物进化启发,提出“模型连接组”作为稀疏先验,仅用1亿词数据即可实现高性能语言学习,展现结构先验在数据效率和人脑对齐上的潜力。 Memorization and Knowledge Injection in Gated LLMs记忆与门控 LLMs 中的知识注入MEGa框架通过门控LoRA模块注入事件记忆,显著缓解灾难性遗忘,接近RAG性能,展示模块化记忆和内部回忆(iRAG)在持续学习中的前景。 AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning OptimizationAdaR1:从长 CoT 到混合 CoT 通过双级自适应推理优化AdaR1通过融合长短CoT模型和双层偏好优化,实现自适应推理,推理长度减半而准确率仅微降,展现“因题施策”的高效推理潜力。完整推介:https://mp.weixin.qq.com/s/MyQN09CEBe59dbKcL7YEQg在小宇宙查看该单集文稿

Episode metadata supplied by the publisher feed · Published May 2, 2025

Embed this episode

NOW PLAYING

AI前沿:从数学推理到记忆注入

0:00 9:29

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of AI可可AI生活?

This episode is 9 minutes long.

When was this AI可可AI生活 episode published?

This episode was published on May 2, 2025.

Can I download this AI可可AI生活 episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!