arXiv:2607. 16821v1 Announce Type: cross Abstract: Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space.
By Irina Piontkovskaia, Sergey Nikolenko
arXiv:2608. 06206v1 Announce Type: cross Abstract: Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscalibration, while exact distribution-free conditional coverage is finite-sample unattainable.
By Anton Conrad, Rustam Isaev, Denis Belomestny, Eric Moulines, Sergey Samsonov
arXiv:2607. 27680v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the standard mechanism for fine-tuning large pretrained models, yet its statistical properties remain only partially understood.
By Arunan J
arXiv:2608. 01460v1 Announce Type: new Abstract: Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability.
By Yuqicheng Zhu, Jialin Yu, Lin Li, Gengyuan Zhang, Zhen Yang, Steffen Staab, Puneet Dokania, Philip Torr, Jie Tang, Evgeny Kharlamov
arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.
By Weijia Han, Lisha Qu
arXiv:2606. 00257v1 Announce Type: cross Abstract: Token-level credit assignment for language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA.
By Rodney Lafuente-Mercado
arXiv:2607. 12501v3 Announce Type: replace Abstract: The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones.
By Paolo Giannitrapani
arXiv:2607. 12438v1 Announce Type: new Abstract: Deep networks trained with label noise often learn clean structure before memorizing corrupted labels.
By Satwik Bathula, Anand A. Joshi
arXiv:2608. 10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept?
By Tingan Jin, Shuhang Dong, Haosong Li, Chung-Hsien Chou
arXiv:2608. 01074v1 Announce Type: new Abstract: Tabular data is used extensively in many real-world use cases.
By Mayank Sharma, Rohit Kumar Mourya, Pratik Mazumder
arXiv:2606. 05169v1 Announce Type: new Abstract: We give a stereological theory of LLM benchmark coverage.
By Jason Z Wang
arXiv:2607. 21372v1 Announce Type: cross Abstract: Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios.
By Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, Pipi Hu