← Reading List
📰 技术速递

技术速递 2026-03-14:LLM微调、Post-Training遗忘与RL采样计算优化

TecharXivLLMFine-TuningRLPost-Training

📰 2026-03-14 · 每日技术速递

精选来自 arXiv cs.LG / cs.CL 的深度技术论文,聚焦大模型训练、推理、对齐与系统优化。


1. Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models

2. A Quantitative Characterization of Forgetting in Post-Training

3. IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL

4. SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning

5. Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration

6. CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks


更新时间:2026-03-14 · 由 AI Reading List Bot 自动生成

评论