arXiv Machine Learning August 7, 2026 By Yue Han, Ziniu Liu

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning

Read the original on arXiv Machine Learning →

arXiv:2608. 05250v1 Announce Type: new Abstract: Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach their best generalization at different times.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv Machine Learning

1d ago

Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

arXiv:2608. 14650v1 Announce Type: new Abstract: Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation.

By Malo de Pastor

arXiv AI

1d ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.

By Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang

llms agents

arXiv Machine Learning

Jun 19

Model soups need only one ingredient

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.

By Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 21

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training

arXiv:2604. 26256v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance block the entire training pipeline.

By Tianhao Hu, Xiangcheng Liu, Yuchun Miao, Youshao Xiao, Hongyu Zang, Yang Zheng, Xuan Huang, Jinrui Ding, Yufei Zhang, Yu Yang, Yi-Kai Zhang, Yueqing Sun, Chengcheng Han, Xiandi Ma, Wei Wang, Qi Gu, Yerui Sun, Yuchen Xie, Xunliang Cai

llms agents reinforcement-learning efficiency benchmarks

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

Jul 21

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers

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

llms fine-tuning

Related stories

Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Model soups need only one ingredient

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training

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

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers