Fine-tuning and adaptation

LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.

8,208 stories · RSS feed

arXiv Machine Learning

Jul 23

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

arXiv:2607. 19604v1 Announce Type: cross Abstract: Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge.

By Nischay Dhankhar, Dos Baha, Abulhair Saparov

llms fine-tuning

arXiv AI

Jul 23

When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarization

arXiv:2607. 19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined.

By Dipto Sumit, Ankan Kumar Roy Srizon, Sadia Khair Rodela, Atia Haque Asha, Mourchona Afrin, Niloy Farhan, Farig Sadeque

nlp fine-tuning efficiency benchmarks safety

arXiv AI

Jul 23

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models

arXiv:2607. 19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely on learned steering objectives or single-criterion feature selection.

By Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan

llms fine-tuning

arXiv AI

Jul 23

Anatomically Faithful but Temporally Diffuse: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography

arXiv:2607. 13738v2 Announce Type: replace-cross Abstract: Deep video models estimate left-ventricular ejection fraction (EF) from echocardiography with near-expert accuracy, and post-hoc attribution is increasingly used to certify that such models look at the right place.

By Hyunkyung Han, Min Jung Kim

llms fine-tuning

arXiv AI

Jul 23

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.

By Jason Vega, Gagandeep Singh

llms fine-tuning safety

arXiv AI

Jul 23

FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation

arXiv:2607. 19354v1 Announce Type: new Abstract: Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier.

By Cy Xie

reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jul 23

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

arXiv:2607. 20027v1 Announce Type: new Abstract: Short-term Heart Rate Variability (HRV) forecasting could provide clinicians with actionable lead time for detecting autonomic dysfunction and adverse cardiac events.

By Luukas Per\"akyl\"a, Fahad Sohrab, Ville Hautam\"aki, Merja Hein\"aniemi, Sui Huang, Pekka Abrahamsson

fine-tuning

arXiv Machine Learning

Jul 23

Variance-reduced Domain Adaptation using Paired Sampling

arXiv:2607. 20367v1 Announce Type: new Abstract: Correlation alignment and the maximum mean discrepancy are two widely used distribution-matching frameworks for unsupervised domain adaptation (UDA).

By Andrea Napoli

fine-tuning safety

arXiv Machine Learning

Jul 23

Statistical Inference for Rank Allocation in Low-Rank Adaptation

arXiv:2607. 20205v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models.

By Yihang Gao, Vincent Y. F. Tan

llms nlp fine-tuning

arXiv Machine Learning

Jul 23

Domain-Adapted Power Curve for Cross-Farm Applications

arXiv:2607. 19744v1 Announce Type: cross Abstract: The wind energy industry relies on accurate power curve models to make power forecast, evaluate turbine performance, quantify upgrade, or support site-planning decisions.

By Ahmadreza Chokhachian, V. Roshan Joseph, Yu Ding

fine-tuning

arXiv AI

Jul 23

Persian Pixel: A large-scale synthetic OCR dataset for Persian language

arXiv:2607. 20385v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) for Persian remains substantially less mature than for Latin-script languages despite Persian being spoken by more than 110 million people across multiple countries.

By Pouria Mahdi, Haq Nawaz Malik

llms computer-vision fine-tuning

arXiv Machine Learning

Jul 23

Online Variance Reduction for Domain Adaptation on Streaming Data

arXiv:2607. 20374v1 Announce Type: new Abstract: This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions.

By Andrea Napoli

fine-tuning safety

arXiv AI

Jul 23

Dominant vs. Dominated: Concept-Level Generative Collapse in Diffusion Models

arXiv:2512. 20666v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models have attracted significant attention for their ability to generate diverse, high-fidelity images.

By Hayeon Jeong, Jong-Seok Lee

diffusion fine-tuning benchmarks

arXiv Machine Learning

Jul 23

Generative AI-enhanced Probabilistic Multi-Fidelity Surrogate Modeling Via Transfer Learning

arXiv:2602. 00072v2 Announce Type: replace Abstract: The performance of machine learning surrogates is critically dependent on data quality and quantity.

By Jice Zeng, David Barajas-Solano, Hui Chen

fine-tuning benchmarks data-engineering

arXiv AI

Jul 23

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

arXiv:2601. 06487v3 Announce Type: replace-cross Abstract: Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.

By Qiang Zhang, Boli Chen, Fanrui Zhang, Ruixue Ding, Shihang Wang, Qiuchen Wang, Yinfeng Huang, Haonan Zhang, Rongxiang Zhu, Pengyong Wang, Ailin Ren, Xin Li, Pengjun Xie, Jiawei Liu, Ning Guo, Jingren Zhou, Zheng-Jun Zha

llms agents reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 23

Reward-Aware Population Scaling of Evolutionary Strategies in LLM Fine-Tuning

arXiv:2607. 19408v1 Announce Type: new Abstract: Using Evolutionary Strategies (ES) for fine-tuning large language models is attractive because it is memory-efficient, parallel, and compatible with black-box or discrete rewards.

By Sung Cho, Gyubin Han

llms fine-tuning

arXiv Machine Learning

Jul 23

Towards Practical Emotion Recognition: An Unsupervised Source-Free Approach for EEG Domain Adaptation

arXiv:2504. 03707v2 Announce Type: replace-cross Abstract: Emotion recognition is crucial for advancing mental health, healthcare, and technologies such as brain-computer interfaces.

By Md Niaz Imtiaz, Naimul Khan

fine-tuning benchmarks safety

arXiv AI

Jul 23

Language-Specific versus Cross-Lingual Knowledge Graphs for Implicit Aspect Identification in Arabic: A Comparative Study of Reasoning and Adaptation Strategies

arXiv:2607. 20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text.

By Lujain A. Alawwad

llms rag nlp fine-tuning benchmarks

arXiv Machine Learning

Jul 23

Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling

arXiv:2607. 20339v1 Announce Type: new Abstract: Constitutive modeling under uncertainty remains a central challenge for reliable mechanics simulations, particularly when the available stress-deformation data are sparse, noisy, or heterogeneous.

By Somesh Pratap Singh, Govinda Anantha Padmanabha, Jingye Tan, Steven Yang, Reese E. Jones, D. Thomas Seidl, Nikolaos Bouklas

fine-tuning

arXiv AI

Jul 23

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.

By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang

llms fine-tuning efficiency multimodal benchmarks

Get the daily briefing