It is found that immediate post-training performance does not reliably predict retention after subsequent fine-tuning, and this supports the view that post-training drives immediate specialization while early exposure improves robustness to later forgetting.
The results suggest that the empirical success of memory replay goes beyond the mitigation of forgetting, actively reintroducing the benefits of data co-observation into the learning process.
Timm Hess, Abhishek Jha, Gido M. van de Ven et al.· 0 citations
A simple modification to supervised fine-tuning, TailSFT, which filters out already fit sequences during training, thereby focusing learning on under-modeled regions, or the tail, of the data distribution, and introduces a lightweight diagnostic for identifying settings where TailSFT is most likely to help.
Sadhika Malladi, Samy Jelassi, Dylan J. Foster et al.· 3 citations
This work deconstructs the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface, and uses the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shape...
D. Clay, Saket Gollapudi, Sankar V Harilal et al.· 1 citation
This paper attempts to build a high-level framework for how animals learn and preserve knowledge by modelling neural components and states that are known to be related to memory consolidation by proposing 4MAS (4 Module Awake/Sleep), a novel macroarchitecture demonstrating how machine learning models might benefit from...
Benjamin Smith, L. Kuhlmann, Kaushik Roy et al.· 0 citations
Remember-R1 is proposed, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory, demonstrating its effectiveness in mitigating long-context visual forgetting.
Jianmin Chen, Jiaqi Tang, Wei Wei et al.· 0 citations
TAILS resolves cross-task ambiguity at the representation level, while leaving the original PTM, method-specific modules, and classifier unchanged, and can improve classification and task-inference performance with modest parameter overhead and negligible inference cost.
Zhiming Xu, Huiyu Yi, Zheng-He Xie et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
