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 21

IndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD

arXiv:2607.28050v2 Announce Type: replace Abstract: Automating industrial CAD design and manufacturing places distinctive demands on multimodal foundation models: the model must see engineering drawi...

By Nianchen Deng, Jiaxin Ai, Tao Hu, Shu Zou, Yurui Dong, Siqi Li, Xinyu Cai, Xuemeng Yang, Licheng Wen, Hongbin Zhou, Hairong Zhang, Pinlong Cai, Botian Shi

llms agents fine-tuning multimodal benchmarks

arXiv AI

Oct 21

When does Subgroup Balance Matter? Predicting Performance Sensitivity from Latent Separability

arXiv:2512.09496v2 Announce Type: replace-cross Abstract: Unequal representation of demographic groups in training data poses challenges to model generalisation across populations. Standard practice...

By Anissa Alloula, Charles Jones, Zuzanna Wakefield-Skorniewska, Francesco Quinzan, Bart{\l}omiej Papie\.z

diffusion fine-tuning

arXiv AI

Oct 21

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

arXiv:2603.00889v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforce...

By Xinyu Zhu, Yihao Feng, Yanchao Sun, Xianzhi Du, Pingzhi Li, Olli Saarikivi, Yun Zhu, Yu Meng

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Oct 21

You Are the Trigger: Speaker-Activated Backdoors

arXiv:2610.27210v1 Announce Type: new Abstract: Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attack...

By Nata\v{s}a Kr\v{c}o, Euodia Dodd, Peter Romov, Yves-Alexandre de Montjoye

llms agents fine-tuning multimodal

arXiv AI

Oct 21

An Empirical Study of Development-Tuned Representation Sensitivity for Medical QA Data Selection

arXiv:2609.09684v2 Announce Type: replace-cross Abstract: We study medical question-answering (QA) data selection when a developer already has questions, labels, and auxiliary explanatory texts but c...

By Yuexin Wu, Dayou Yu, Vasile Rus

fine-tuning benchmarks

arXiv Machine Learning

Oct 21

OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning

arXiv:2510.13003v2 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates inter...

By Yifeng Xiong, Xiaohui Xie

llms fine-tuning safety

arXiv Machine Learning

Oct 21

Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases

arXiv:2610.27150v1 Announce Type: cross Abstract: As two most prevalent neurodegenerative diseases (NDDs), Alzheimer's disease (AD) and Parkinson's disease (PD) shared commonalities both in symptomol...

By Yuji Zhao, Boris Gutman

fine-tuning

arXiv Machine Learning

Oct 21

Guided Diffusion for Trustworthy Synthetic Text Generation

arXiv:2610.27259v1 Announce Type: cross Abstract: The rapid evolution of Large Language Models is fueled by massive datasets, yet this reliance poses severe privacy risks, as models can inadvertently...

By Qi Pang, Hanshen Xiao, Andre Manoel, Lipika Ramaswamy, Wenting Zheng, Virginia Smith, G. Edward Suh

llms rag diffusion fine-tuning safety

arXiv Machine Learning

Oct 21

MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning

arXiv:2610.27491v1 Announce Type: cross Abstract: Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit withou...

By Kohei Yamamoto, Kosuke Okusa

fine-tuning efficiency safety

arXiv Machine Learning

Oct 21

ProVe: Proposer-Verifier Decoding

arXiv:2610.27815v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive (AR) language models by letting a small model draft tokens serially and a large model verify them in...

By Ziqi Jin, Weiwen Xu, Jiaxi Li, Yujie Zhong, Qi She, Aixin Sun

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Oct 21

Confessions of a Masked MDP

arXiv:2610.28360v1 Announce Type: cross Abstract: In reinforcement learning, one presumes the action set to be known ahead of time, and, thus, one must know if any state-action pairs are not permissi...

By Sebastian Reboul, Lorenzo Croissant, H\'el\`ene Halconruy

reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 21

FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model

arXiv:2410.13925v2 Announce Type: replace Abstract: \textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often fac...

By ZiDong Wang, Zeyu Lu, Di Huang, Cai Zhou, Xiaoyu Yue, Wanli Ouyang, and Lei Bai

llms diffusion computer-vision fine-tuning

arXiv Machine Learning

Oct 21

Follow the Mean: Reference-Guided Flow Matching

arXiv:2605.10302v4 Announce Type: replace Abstract: Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching a...

By Pedro M. P. Curvo, Maksim Zhdanov, Floor Eijkelboom, Jan-Willem van de Meent

diffusion fine-tuning

arXiv Computation and Language

Oct 21

Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition

arXiv:2610.26888v1 Announce Type: new Abstract: We present Mixture of Phonetic Experts based Low-Rank Adaptation (MoPE-LoRA), a parameter-efficient adaptation framework for accented English speech re...

By Santosh Dahal, Anmol Guragain, Tianchi Liu, Luis Fernando D'Haro, Kiran Chandra Dahal

fine-tuning multimodal

arXiv Computation and Language

Oct 21

Evaluating Tibetan Speech Recognition Across Dialects and Adaptation Regimes: A Multi-Granularity Analysis

arXiv:2610.27002v1 Announce Type: new Abstract: Tibetan speech recognition is usually evaluated with character or syllable error rates because the writing system does not mark word boundaries. These...

By Jacob Moore, Sheng Li

computer-vision fine-tuning multimodal

arXiv Computation and Language

Oct 21

GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models

arXiv:2610.28457v1 Announce Type: cross Abstract: General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world intera...

By Ziyong Wang, Yupei Lin, Runxuan Huang, Liang Lin, Dongyu Zhang, Guangrun Wang

llms robotics fine-tuning multimodal benchmarks

arXiv Computer Vision

Oct 21

AdaptMIL: Domain Adaptation for Multiple Instance Learning in Digital Pathology

arXiv:2610.28007v1 Announce Type: new Abstract: Pathology foundation models (PFMs) support a wide range of histopathology tasks on whole-slide images through multiple instance learning (MIL). Despite...

By Ben Vardi, Dana Schonberger, Yuval Friedmann, Zohar Yakhini, Iris Barshack, Alexander Loebel, Ariel Shamir

fine-tuning safety

arXiv Computer Vision

Oct 21

SolarRenderer: Few-Step Generative Reference Rendering

arXiv:2610.28630v1 Announce Type: new Abstract: Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a...

By Guian Fang, Shengju Qian, Dongyue Lu, Junchao Huang, Lutao Jiang, Xin Wang, Yiren Song, Li Jiang, Mike Zheng Shou

agents fine-tuning efficiency benchmarks

arXiv Computer Vision

Oct 21

Codec-Compatible Learned Compression for 3D Gaussian Splatting

arXiv:2610.26920v1 Announce Type: cross Abstract: Video-based 3D Gaussian Splatting (3DGS) compression methods provide a practical route by representing Gaussian attributes as 2D maps and coding them...

By Feiyang Yu, Qi Yang, Wenjie Huang, Yunfeng Guan, Yiling Xu, Zhu Li

fine-tuning

arXiv Computer Vision

Oct 21

Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training

arXiv:2610.28474v1 Announce Type: new Abstract: People adapt how they talk to the person in front of them. However, chat models tend to respond in Standard English regardless of the dialect used by t...

By Zhizhuo Kou, Heming Li, Jian Yang, Junyu Luo, Jingshu Peng, Sirui Han, Yike Guo

reinforcement-learning fine-tuning

Get the daily briefing