arXiv Machine Learning June 19, 2026 By Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard

Model soups need only one ingredient

Read the original on arXiv Machine Learning →

arXiv:2602. 09689v2 Announce Type: replace Abstract: Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

4d ago

Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories

arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...

By Zhehao Huang, Changxin Tian, Qingyuan Yang, Kunlong Chen, Ziqi Liu, Zhiqiang Zhang, Xiaolin Huang, Jun Zhou

llms safety

Hugging Face Trending Papers

Jul 13

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jul 14

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.

By Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey, Bang An, Bernard Ghanem, Yibo Yang

llms fine-tuning benchmarks safety

arXiv AI

Jun 18

From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging

arXiv:2506. 14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets.

By Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite

fine-tuning

arXiv AI

Aug 14

Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking

arXiv:2605. 18852v2 Announce Type: replace-cross Abstract: Selecting a final checkpoint for multimodal large language models (MLLMs) is challenging when late-stage candidates are closely matched and downstream evaluation signals are noisy.

By Qinwu Xu, Zhuoheng Li, Jessie Salas

llms agents computer-vision multimodal

arXiv Computer Vision

3d ago

Reliability-Aware Checkpoint Selection for Domain Generalization

arXiv:2609.39934v1 Announce Type: cross Abstract: Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable proba...

By Jinshi Liu, Jiahao Li, Pan Liu, Yanfeng Li, Rui Qian, Zhao Tong, Yue Sun, Tao Tan

benchmarks

One email a morning, machine-written

Related stories

Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging

Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking

Reliability-Aware Checkpoint Selection for Domain Generalization