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

AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents

arXiv:2607. 02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges.

By La\"ila Elkoussy (LRE, EPITA), Julien Perez (LRE)

llms agents fine-tuning benchmarks safety

arXiv AI

Jul 7

RADIO1D: Elastic Representations for Condensed Vision Modeling

arXiv:2607. 03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.

By Greg Heinrich, Mike Ranzinger, Collin McCarthy, Natan Bagrov, Eugene Khvedchenya, Bryan Catanzaro, Jan Kautz, Andrew Tao, Pavlo Molchanov

llms nlp fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 7

Efficient Perception in Automotive Detection and Tracking Using Neuromorphic Computing

arXiv:2607. 04921v1 Announce Type: cross Abstract: Deep learning algorithms are notorious for their high carbon footprint and computational demands that limit their deployment on edge devices and raise concerns about their long-term sustainability.

By Manish Kolachalam, Rani Malhotra

agents computer-vision fine-tuning

arXiv Machine Learning

Jul 7

What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation

arXiv:2607. 04726v1 Announce Type: cross Abstract: Chart-to-code generation is commonly trained with supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable target.

By Tianhao Niu, Qingfu Zhu, Wanxiang Che

fine-tuning safety

arXiv AI

Jul 7

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

arXiv:2607. 05377v1 Announce Type: cross Abstract: While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations.

By Jiaqi Peng, Xiqian Yu, Delin Feng, Yuqiang Yang, Wenzhe Cai, Jing Xiong, Ganlin Yang, Jinliang Zheng, Jiafei Cao, Xueyuan Wei, Jiangmiao Pang, Yuan Shen, Tai Wang

agents robotics fine-tuning multimodal

arXiv AI

Jul 7

Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models

arXiv:2512. 14926v2 Announce Type: replace-cross Abstract: Focusing on low-resource languages is an essential step toward democratizing generative AI.

By George-Andrei Dima, R\u{a}zvan-Alexandru Sm\u{a}du, Dumitru-Clementin Cercel

llms nlp fine-tuning multimodal

arXiv AI

Jul 7

Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models

arXiv:2607. 03591v1 Announce Type: cross Abstract: Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured crash records.

By Ryosei Tamura, Andrew Shin

llms agents computer-vision fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 7

NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation

arXiv:2607. 04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA.

By Junjie Tang, Jun Huan, Hao Zhou, Yuhao Zhang, Lin Wang

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jul 7

Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning

arXiv:2607. 05300v1 Announce Type: new Abstract: Parameter-efficient fine-tuning still leaves a broad space of behavior-changing updates reachable, so a poisoned objective can be represented and optimized.

By Fabien Polly

fine-tuning

arXiv AI

Jul 7

Revealing Hidden Model Behaviors with Task-Specific Self-Reports

arXiv:2607. 03640v1 Announce Type: cross Abstract: Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic.

By Taras Kutsyk, Bartosz Zieli\'nski

llms fine-tuning safety

arXiv AI

Jul 7

CogAdapt: Adapting Clinical ECG Foundation Models for Wearable Cognitive Load Assessment

arXiv:2605. 22774v3 Announce Type: replace-cross Abstract: Assessing cognitive load continuously and at low latency would help adaptive human-computer interaction, but it remains hard because labeled data are scarce and models generalize poorly across subjects.

By Amir Mousavi, Erfan Nourbakhsh, Mohammad Sadegh Sirjani, Mimi Xie, Rocky Slavin, Leslie Neely, John Davis, John Quarles

fine-tuning

arXiv AI

Jul 7

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training

arXiv:2607. 04574v1 Announce Type: cross Abstract: For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on.

By Junze Ye, Jiayi Cheng, Miao Lu, Michal Mankowski, Jose Blanchet, Mohsen Bayati

llms agents fine-tuning

arXiv AI

Jul 7

Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding

arXiv:2607. 04383v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set.

By Zihan Zhang, Xize Cheng, Wenhao Yan, Tong Zhang, Dongjie Fu, Boyun Zhang, Yongbo He, Tao Jin

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 7

Out-of-Distribution Generalization of Risk Aversion in Language Models

arXiv:2607. 02755v1 Announce Type: cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned.

By Kristina Zhang, Junior Chinomso Okoroafor, Benjamin Maltbie, Andrew Lin, Abhitej Bokka, Elliott Thornley

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jul 7

Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types

arXiv:2607. 03304v1 Announce Type: cross Abstract: Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets.

By Paria Vali Zadeh, Sven Tomforde

fine-tuning

arXiv AI

Jul 7

MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs

arXiv:2607. 03932v1 Announce Type: cross Abstract: LLMs can be conveniently adapted to a diverse set of tasks, e.

By Shubhadip Nag, Srinjoy Das, Agniva Saha, Anushree Ghosh, Soumi Das, Tarun Kumar, Suparna Bhattacharya, Sourangshu Bhattacharya

llms fine-tuning benchmarks safety

arXiv AI

Jul 7

Signal from Space: Detecting Schools and Towers to Bridge the Digital Divide

arXiv:2607. 02724v1 Announce Type: cross Abstract: Reliable internet access is essential for modern education, yet millions of school-aged children especially in developing regions remain offline due to unconnected schools.

By Zakarya Elmimouni, Sandor Farkas, Fares Fourati, Vladimir Daigele, Walid Mathlouthi, Mohamed-Slim Alouini

computer-vision fine-tuning

arXiv AI

Jul 7

Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions

arXiv:2607. 03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cyber investigation.

By Eduardo Almeida Palmieri, Mohamed Chahine Ghanem, Dipo Dunsin, Zubair Baig, Ed de Quincey, Kim-Kwang Raymond Choo

llms rag agents nlp fine-tuning multimodal benchmarks safety

arXiv AI

Jul 7

STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition

arXiv:2607. 03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, cloud inference adds latency and privacy risk, and fine-tuned LLM pipelines turn general-purpose models into task-specific classifiers.

By Nirhoshan Sivaroopan, Albert Zomaya, Kanchana Thilakarathna

llms rag nlp fine-tuning benchmarks safety

arXiv AI

Jul 7

A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning

arXiv:2607. 03600v1 Announce Type: cross Abstract: Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains.

By Sushant Dagaji Desale, Rahul Mishra, Ashutosh Kumar Sinha

reinforcement-learning fine-tuning benchmarks safety

Get the daily briefing