Fine-tuning and adaptation

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

3,943 stories · RSS feed

arXiv Machine Learning

Jun 5

Harnessing Source Heterogeneity for Cluster-Structured Transfer Learning

arXiv:2606. 05258v1 Announce Type: cross Abstract: Transfer learning is a natural strategy when a target population has limited data but multiple related auxiliary sources are available.

By Xiaohui Yin, Jun Jin, Shane J. Sacco, Robert H. Aseltine, Kun Chen

fine-tuning

arXiv Machine Learning

Jun 5

An accurate nucleic acid-small molecule docking framework via geometric deep learning with large-scale pretraining

arXiv:2606. 05198v1 Announce Type: cross Abstract: Nucleic acids are increasingly recognized as therapeutic targets beyond conventional protein-centered drug discovery, yet accurate and efficient docking of small molecules to nucleic acid structures remains challenging.

By Shi Li (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China), Xujun Zhang (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China), Mingquan Liu (Faculty of Health Sciences, University of Macau, Macau SAR, China), Hui Zhang (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Shanghai Innovation Institute, Shanghai, China), Shuoying Jia (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Shanghai Innovation Institute, Shanghai, China), Yu Kang (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Shanghai Innovation Institute, Shanghai, China), Tingjun Hou (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Zhejiang Provincial Key Laboratory for Intelligent Drug Discovery and Development, Jinhua Institute of Zhejiang University, Zhejiang, China), Peichen Pan (College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang, P. R. China, Zhejiang Provincial Key Laboratory for Intelligent Drug Discovery and Development, Jinhua Institute of Zhejiang University, Zhejiang, China)

fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

arXiv:2605. 16138v2 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost.

By Jason Weitz, Dmitri Demler, Benjamin Hawks, Aaron Wang, Nhan Tran, Javier Duarte

agents fine-tuning efficiency

arXiv Machine Learning

Jun 5

The Language of Elution: Autoregressive Prediction of the Next Feature in Untargeted LC-HRMS Lipidomics

arXiv:2606. 05225v1 Announce Type: cross Abstract: Untargeted liquid chromatography-high-resolution mass spectrometry (LC-HRMS) detects thousands of molecular features per sample, yet only 2-20% receive confident structural annotations.

By Dayanjan S. Wijesinghe

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning

arXiv:2507. 12612v3 Announce Type: replace Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks.

By Prateek Chanda, Saral Sureka, Parth Pratim Chatterjee, Krishnateja Killamsetty, Nikhil Shivakumar Nayak, Ganesh Ramakrishnan

llms fine-tuning

arXiv Machine Learning

Jun 5

Binary Gaussian Copula Synthesis: an LLM-powered data augmentation framework for early dialysis prediction in chronic kidney disease

arXiv:2403. 00965v2 Announce Type: replace-cross Abstract: Only a small fraction of patients with chronic kidney disease (CKD) progress to dialysis, creating severe class imbalance that limits the performance of machine learning models for early dialysis prediction.

By Hamed Khosravi, Milad Khanchi, Mobina Noori, Srinjoy Das, Abdullah Al-Mamun, Imtiaz Ahmed

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 5

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

arXiv:2606. 06303v1 Announce Type: new Abstract: Controllable generation with discrete diffusion models is often hindered by high computational overhead or the need for retraining.

By Hongkun Dou, Zike Chen, Fengji Li, Hongjue Li, Yue Deng

diffusion fine-tuning benchmarks

arXiv Machine Learning

Jun 5

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.

By Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

llms rag agents fine-tuning safety

arXiv Machine Learning

Jun 5

PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction

arXiv:2604. 01349v4 Announce Type: replace Abstract: Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation trajectories and cannot exploit this unlabeled structure.

By Brandon Yee, Pairie Koh

rag fine-tuning

arXiv Machine Learning

Jun 5

No Need to Train Your RDB Foundation Model

arXiv:2602. 13697v2 Announce Type: replace-cross Abstract: Relational databases (RDBs) contain vast amounts of heterogeneous tabular information that can be exploited for predictive modeling purposes.

By Linjie Xu, Yanlin Zhang, Quan Gan, Minjie Wang, David Wipf

llms fine-tuning data-engineering

arXiv Machine Learning

Jun 5

RREDCoT: Segment-Level Reward Redistribution for Reasoning Models

arXiv:2606. 06475v1 Announce Type: new Abstract: Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning.

By Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger, Sepp Hochreiter

llms computer-vision reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 5

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model

arXiv:2606. 05899v1 Announce Type: new Abstract: We develop a high-dimensional statistical theory of low-rank adaptation (LoRA) in attention models, capturing the interplay between pre-training and fine-tuning.

By O. Duranthon, F. Boncoraglio, L. Zdeborov\'a

fine-tuning safety

arXiv Machine Learning

Jun 5

TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning

arXiv:2606. 06494v1 Announce Type: new Abstract: Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning.

By Marius Dragoi, Ioana Pintilie, Alexandra Dragomir, Antonio Barbalau, Florin Brad

fine-tuning

arXiv Machine Learning

Jun 5

Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation

arXiv:2606. 05988v1 Announce Type: new Abstract: Reasoning models produce long chain-of-thought traces that are costly to distill and encourage verbose student outputs.

By Maxime Griot, Paul Steven Scotti, Tanishq Mathew Abraham

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 5

MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry

arXiv:2606. 05693v1 Announce Type: new Abstract: Large language models (LLMs) have shown promise for molecular property prediction, but their ability to reason over chemical structures remains limited, as molecular representations such as SMILES differ substantially from the natural language on which LLMs are primarily trained.

By Joey Chan, Wonbin Kweon, Ashley Shin, Niharika Bhattacharjee, Pengcheng Jiang, Yue Guo, Jiawei Han

llms rag fine-tuning

arXiv Machine Learning

Jun 5

Is Diversity All You Need for Scalable Robotic Manipulation?

arXiv:2507. 06219v2 Announce Type: replace-cross Abstract: Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood.

By Modi Shi, Li Chen, Jin Chen, Yuxiang Lu, Chiming Liu, Guanghui Ren, Ping Luo, Di Huang, Maoqing Yao, Hongyang Li

computer-vision nlp robotics fine-tuning

arXiv Machine Learning

Jun 5

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

arXiv:2511. 21338v2 Announce Type: replace Abstract: Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in principle, should enable more uniform context utilisation.

By Julianna Piskorz, Cristina Pinneri, Alvaro Correia, Motasem Alfarra, Risheek Garrepalli, Christos Louizos

llms diffusion fine-tuning safety

arXiv Machine Learning

Jun 5

In-Training Defenses against Emergent Misalignment in Language Models

arXiv:2508. 06249v3 Announce Type: replace Abstract: Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EM): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target domain.

By David Kacz\'er, Magnus J{\o}rgenv{\aa}g, Clemens Vetter, Esha Afzal, Robin Haselhorst, Lucie Flek, Florian Mai

llms fine-tuning

arXiv Machine Learning

Jun 5

Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

arXiv:2606. 05516v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers.

By Wanhao Yu, Ziyan Wang, Zheng Wang, Abeer Matar Almalky, Yihang Zuo, Shuteng Niu, Sen Lin, Adnan Siraj Rakin, Deliang Fan, Li Yang

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 5

State commitment learning: training language models to distinguish computation from memory

arXiv:2606. 05201v1 Announce Type: new Abstract: Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions.

By Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang

llms reinforcement-learning fine-tuning

Get the daily briefing