Learning to Remember — Lawrence Feng
Two models can look identical at the end of post-training and diverge once you fine-tune them. That is, how a capability was acquired affects how much of it survives. In our work, we leverage this perspective to identify training choices that push the retention–adaptation tradeoff outward.
COLM 2026 Early data exposure improves robustness to subsequent fine-tuning. Two models can look identical at the end of post-training and diverge once you fine-tune them. That is, how a capability was acquired affects how much of it survives. In our work, we leverage this perspective to identify training choices that push the retention–adaptation tradeoff outward. Part I · The setup Downstream forgetting is an upstream problem. When a post-trained model is released for downstream fine-tuning, its carefully acquired capabilities are at risk. Fine-tuning on a new objective routinely…
saved by
related reading
- Generalization Dynamics of LM Pre-training — Jiaxin Wenjiaxin-wen.github.io
- Early Data Exposure Improves Robustness to Subsequent Fine-Tuningarxiv.org
- SFT, RL, and On-Policy Distillation Through a Distributional Lens | whnrehiew.github.io
- LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
- The Continual Learning Problemjessylin.com
- On-Policy Distillation - Thinking Machines Labthinkingmachines.ai
- Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Modelsarxiv.org
- Recent Advances in Language Model Fine-tuningruder.io
- [2509.14786] Pre-training under infinite computearxiv.org
- [2606.07527] Post-training is (Massive) Supervised Learningarxiv.org
- [2106.09685] LoRA: Low-Rank Adaptation of Large Language Modelsarxiv.org
- [2605.15220] Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Timearxiv.org