Fine-tuning and adaptation

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

8,201 stories · RSS feed

arXiv AI

Oct 15

Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning

arXiv:2407.12703v5 Announce Type: cross Abstract: Fine-tuning pre-trained language models (PLMs) has recently shown a potential to improve knowledge graph completion (KGC). However, most PLM-based me...

By Youmin Ko, Hyemin Yang, Taeuk Kim, Hyunjoon Kim

llms fine-tuning benchmarks safety

arXiv Machine Learning

Oct 15

Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs

arXiv:2610.19968v1 Announce Type: new Abstract: Federated fine-tuning enables large language models (LLMs) to learn collaboratively from distributed client data, but malicious client updates can comp...

By Shuaijie Ma, Yongkang Hu, Yu Cheng, Jiuan Zhou, Yi Xie, Yushuo Zhang, Zhaoxia Yin

llms fine-tuning benchmarks safety

arXiv AI

Oct 15

ReTerm: Recovery Training for Self-Improving Terminal Agents

arXiv:2610.18484v1 Announce Type: new Abstract: Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution...

By Wei Xie, Kaituo Feng, Shiming Fu, Yong Liu, Xiangyu Yue, Shuangjia Zheng

agents reinforcement-learning fine-tuning data-engineering

arXiv Machine Learning

Oct 15

MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search

arXiv:2603.00720v2 Announce Type: replace Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptatio...

By Minkyoung Cho, Insu Jang, Shuowei Jin, Zesen Zhao, Adityan Jothi, Ethem F. Can, Min-Hung Chen, Z. Morley Mao

llms fine-tuning multimodal

arXiv Computation and Language

Oct 15

Gray-Box Hallucination Detection in LLMs with Token Identities

arXiv:2610.19996v1 Announce Type: new Abstract: Large language models often produce fluent but factually incorrect output. Gray-box detectors identify such hallucinations from the token-probability s...

By Shaked Goldshtein, Yitzchak Grunbaum, Fabrizio Frasca, Guy Bar-Shalom, Haggai Maron

llms fine-tuning benchmarks safety

arXiv AI

Oct 15

GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models

arXiv:2610.14541v1 Announce Type: cross Abstract: Emerging strong Vision-Language Models (VLMs) have advanced navigation foundation models. However, these models still have unsatisfactory performance...

By Shaohao Zhu, Wensi Huang, Siqi Zhang, Yuqiang Yang, Meng Wei, Chenyang Wan, Tianle Liu, Tai Wang, Jinming Xu

llms robotics fine-tuning multimodal benchmarks

arXiv Machine Learning

Oct 15

RM-OPD: On-Policy Distillation for Generative Reward Models

arXiv:2610.20174v1 Announce Type: new Abstract: Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Model...

By Qinglin Su, Licheng Pan, Zhen Fang, Jiakang Wang, Qingnan Ren, Yunsheng Lu, Yan Gao, Zhixuan Chu

reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Oct 15

Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models

arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the context...

By S. M. Mahbub Uddin Ahmed

llms fine-tuning efficiency benchmarks safety

arXiv AI

Oct 15

ZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes

arXiv:2610.15336v1 Announce Type: cross Abstract: Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, deb...

By Lisong He, Yunxuan Jiang, Haishan Ye, Xiangyu Chang

llms fine-tuning

arXiv AI

Oct 15

Recursive Environment Scaling for General Long-Horizon Agents

arXiv:2610.16397v1 Announce Type: new Abstract: We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environ...

By Lingxiao Jing, Zhengbo Jiao, Yichen Xiang, Bofan Zhu, Lingbei Meng, Yan Ni, Haorui Chen, Ran Ran, Zhirong Shen, Yuheng Yang, Chenhang Cui, Yaosong Du, Rui Huang

agents fine-tuning benchmarks

arXiv Computer Vision

Oct 15

MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs

arXiv:2610.18870v2 Announce Type: replace Abstract: We generally perceive that training text-to-image diffusion models requires heavy compute: it is true if we aim at a comprehensive frontier model....

By Reyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang, Liang Zheng

llms diffusion fine-tuning

arXiv AI

Oct 15

TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training

arXiv:2610.17726v1 Announce Type: cross Abstract: Large language model (LLM) agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning--acquiring new...

By Yuqian Fu, Kaiwen Jiang, Zijun Song, Jiawei Wang, Yuanheng Zhu, Dongbin Zhao

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Oct 15

ARMED: Adaptive Retrieval-Augmented Medication Recommendation

arXiv:2610.16440v1 Announce Type: cross Abstract: Medication recommendation requires jointly considering diagnoses, comorbidities, longitudinal patient history, and treatment interactions. Although r...

By Kyungkeon Chung, Se Un Park, Hyejin Lee, Junyoung Park

llms rag fine-tuning

arXiv AI

Oct 15

Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models

arXiv:2610.17310v1 Announce Type: new Abstract: Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral pattern...

By Hanbo Xie, Yue Zhao, Robert C. Wilson

llms agents fine-tuning benchmarks

arXiv AI

Oct 15

Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments

arXiv:2610.16867v1 Announce Type: cross Abstract: Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were ach...

By Xiaoyang Yuan, Ji Zhao, Xingyu Hu, Wenhan Wang, Yutao Hu, Qiaosheng Zhang, Pengfei Liu, Yu Qiao, Yi Bin, Wenqi Shao

agents fine-tuning benchmarks

arXiv AI

Oct 15

SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection

arXiv:2610.16957v1 Announce Type: cross Abstract: Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearl...

By Niyazi Ahmet Metin, Dilara Kek\"ull\"uo\u{g}lu

llms fine-tuning

arXiv AI

Oct 15

MedEvo: Medical Reasoning Evolution through Knowledge Navigation

arXiv:2610.17690v1 Announce Type: new Abstract: Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed traje...

By Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng, Quanbin Wang, Jiangwei Lao, Yingao Liu, Jiajia Liu, Jinming Cao, Honglin Lin, Zhihong Lu, Hao Jin, Jian Wang, Lijun Wu

fine-tuning efficiency multimodal benchmarks

arXiv Machine Learning

Oct 15

HankelKANet: Lightweight Path Loss Estimation via Physics-Inspired Hankel Convolution

arXiv:2610.19524v1 Announce Type: new Abstract: Accurate path loss (PL) estimation is essential for wireless network planning and optimization. This paper proposes HankelKANet, a lightweight physics-...

By Yue Ruan, Xiaoxiao Cheng, Yunan Zhu, Wenlong Huang, Meng Hua

fine-tuning benchmarks

arXiv AI

Oct 15

To Align or Not To Align: Check Your COMPASS Before You Train

arXiv:2610.18638v1 Announce Type: new Abstract: Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tu...

By Fabian Gr\"oger, Petar Damjanovi\'c, Maria Brbi\'c

llms fine-tuning multimodal safety

arXiv AI

Oct 15

FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation

arXiv:2610.17191v1 Announce Type: cross Abstract: Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stor...

By Zekun Shi, Alastair James Arthur Price

fine-tuning

Get the daily briefing