The Flow has not summarised this story yet — read it at arXiv Machine Learning.
arXiv:2607. 26628v1 Announce Type: new Abstract: TabPFN performs classification through in-context learning: it conditions on a set of labeled training rows (the context, or prototypes) and predicts test labels without gradient updates.
arXiv:2610.14028v1 Announce Type: cross Abstract: Data selection for LLM fine-tuning faces two facts about real training: data pools draw from many distinct domains, and evaluation spans diverse task...
Data-DPO is a target model‑oriented supervised fine‑tuning data selection method that uses one‑step probing of the target model to generate pairwise data preferences, trains a lightweight reward model to capture these preferences, and then selects a training subset by combining target‑model preference, external quality scores, and marginal diversity. Experiments on Vision‑Flan and LLaVA‑CoT demonstrate that Data‑DPO consistently outperforms existing data selection baselines across multiple data budgets and even surpasses full data training performance.
The paper introduces Dr. Post-Training, a framework that treats general training data as a data‑induced regularizer to prevent overfitting to scarce target objectives, rather than merely a pool for selection. It constructs a feasible set of model update directions from general data and projects target‑driven updates onto this set, unifying standard training and existing data‑selection methods as special cases along a bias‑variance spectrum. Experiments on SFT, RLHF, and RLVR demonstrate that these methods outperform both standard training and state‑of‑the‑art data‑selection baselines, especially when general and target data are highly misaligned, while system optimizations keep overhead minimal.
arXiv:2610.28556v1 Announce Type: cross Abstract: Large language models (LLMs) can leverage semantic feature names alongside summary statistics for tabular feature selection, yet it remains unclear w...
arXiv:2609.35793v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR). An exact verifier can also support te...