Fine-tuning and adaptation

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

3,721 stories · RSS feed

arXiv AI

Jul 7

Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention

arXiv:2607. 04422v1 Announce Type: cross Abstract: Recent NVFP4 pretraining methods mainly target transformer linear layers, leaving optimizer states, optimizer arithmetic and attention underexplored in 4-bit pipelines.

By Siyu Ding, Mingchuan Ma, Jiabo Tong, Xingrun Xing, Ziming Wang, Guoqi Li

llms fine-tuning efficiency safety

arXiv AI

Jul 7

One Framework for All: Cross-Modal Membership Inference for Generative Models

arXiv:2607. 04339v1 Announce Type: cross Abstract: Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks.

By Dayong Ye, Tainqing Zhu, Kun Gao, Junhao Liu, Yichuan Chen, Shuai Zhou, Hengzhu Liu, Bo Liu, Wanlei Zhou

rag diffusion fine-tuning multimodal benchmarks safety

arXiv AI

Jul 7

CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving

arXiv:2607. 04179v1 Announce Type: cross Abstract: End-to-end Vision-Language Models (VLMs) show immense potential in autonomous driving.

By Zhaohong Liu, Hao Ye, Xianlin Zhang, Mengshi Qi

llms agents reinforcement-learning robotics fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 7

Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory

arXiv:2607. 04118v1 Announce Type: cross Abstract: With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often introduce additional training, deployment, and maintenance overhead.

By Fengxian Ji, Zhuohan Xie, Jingpu Yang, Fan Zhang, Zirui Song, Xiuying Chen

fine-tuning

arXiv AI

Jul 7

EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention

arXiv:2508. 16771v3 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically salient code.

By Yifan Zhang, Chen Huang, Yueke Zhang, Jiahao Zhang, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang

llms nlp fine-tuning benchmarks

arXiv AI

Jul 7

KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment

arXiv:2607. 03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates.

By Jinkyeong Choi, Chaebin Jeong, Donghyeon Park

llms fine-tuning benchmarks safety

arXiv AI

Jul 7

A Multi-Task Deep Learning Framework for Real-Time Intelligent Video Surveillance with Temporal Event Validation

arXiv:2607. 03131v1 Announce Type: cross Abstract: Modern video surveillance systems generate far more video streams than human operators can effectively monitor, making automated analysis essential for timely detection of security events.

By Estera Dumitru, Stelian Sp\^inu

fine-tuning

arXiv AI

Jul 7

SNR-Adaptive Unified Diffusion for Multi-Task Medical Image Segmentation

arXiv:2607. 03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks.

By Jiahao Liu, Hang Wei, Shuai Wu

diffusion computer-vision fine-tuning benchmarks safety

arXiv Machine Learning

Jul 7

AMT-APC: Automatic Piano Cover by Fine-Tuning an Automatic Music Transcription Model

arXiv:2409. 14086v2 Announce Type: replace-cross Abstract: There have been several studies on automatically generating piano covers, and recent advancements in deep learning have enabled the creation of more sophisticated covers.

By Kazuma Komiya, Yoshihisa Fukuhara

fine-tuning

arXiv AI

Jul 7

No Time Like the Present: Agentic Test-Time Training for LLM Agents

arXiv:2607. 03441v1 Announce Type: cross Abstract: LLM agents often degrade over long episodes: as trajectories grow, they revisit explored states, repeat failed actions, and lose strategies that previously worked.

By Yanbo Wang, Jinhua Hao, Yuze Shi, Kun Yuan, Ming Sun

llms agents fine-tuning

arXiv AI

Jul 7

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs

arXiv:2607. 04854v1 Announce Type: new Abstract: Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications.

By Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 7

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

arXiv:2607. 02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge.

By Jiyang Guan, Yong Xie, Jun Chen, Jiexi Liu, Zipeng Ye, Defeng Li, Jiayu Shen, Jialing Tao, Hui Xue

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 7

Pretraining Curricula Enable Selective Fine-tuning

arXiv:2607. 04846v1 Announce Type: cross Abstract: Transformers follow implicit curricula whereby some tasks are learned before others.

By Sebastian A. Bruijns, Jirko Rubruck, Mia H. Whitefield, Kai J. Sandbrink, Fazl Barez, Christopher Summerfield

llms fine-tuning safety

arXiv AI

Jul 7

Query2Diagram: Answering Developer Queries with UML Diagrams

arXiv:2604. 23816v2 Announce Type: replace-cross Abstract: Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems.

By Oleg Baryshnikov, Anton M. Alekseev, Sergey I. Nikolenko

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 7

Transfer Learning in High-dimensional Ising Models

arXiv:2607. 03005v1 Announce Type: new Abstract: In high-dimensional Ising model estimation, target sample sizes are often limited, and effectively using auxiliary binary datasets of unknown relevance remains challenging.

By Joonho Kim, Seyoung Park

fine-tuning

arXiv Machine Learning

Jul 7

When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters

arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.

By Nicholas Tan Jerome, Frank Simon

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 7

OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction

arXiv:2604. 16878v2 Announce Type: replace Abstract: Early prediction of severe clinical deterioration and remaining length of stay can enable timely intervention and better resource allocation in high-acuity settings such as the ICU.

By Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee, Sang Kyu Kim, Irene Y. Chen

fine-tuning efficiency multimodal benchmarks

arXiv AI

Jul 7

Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models

arXiv:2607. 04546v1 Announce Type: cross Abstract: Action-conditioned world models allow robots to predict the future consequences of candidate actions without additional physical interaction, supporting policy evaluation, planning, and data augmentation.

By Riccardo O. Feingold, Davide Liconti, Chenyu Yang, Robert K. Katzschmann

diffusion computer-vision robotics fine-tuning benchmarks

arXiv AI

Jul 7

NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO

arXiv:2607. 03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason.

By Xinqi Zhang

llms fine-tuning benchmarks

arXiv AI

Jul 7

Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

arXiv:2607. 02909v1 Announce Type: cross Abstract: Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language.

By Hulingxiao He, Zhi Tan, Yuxin Peng

llms rag fine-tuning multimodal

Get the daily briefing