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

StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning

arXiv:2610.16451v1 Announce Type: cross Abstract: Fine-tuning large language models at scale is increasingly limited by the memory cost of backpropagation. Zeroth-Order (ZO) optimizers reduce this bu...

By Xuanlin Yang, Jia Li, Zhouchen Lin

llms fine-tuning

arXiv AI

Oct 15

PATMT2: Two-stage domain adaptation for multilingual patent translation

arXiv:2610.16466v1 Announce Type: cross Abstract: We present PatMT2 (Patent Machine Translation, v2), a two-stage LoRA pipeline that adapts the Hy-MT2-7B dedicated translation model to four-language...

By Xiaowei Su, Xusen Cheng

nlp fine-tuning

arXiv AI

Oct 15

Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation

arXiv:2610.17573v1 Announce Type: cross Abstract: Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fi...

By Jiaqi Tang, Yu Wang, Yang Liu, Jing Tao, Fandong Zhang, Zhou Zhen, Xiahai Zhuang, Qingchao Chen, Yining Yang, Yizhou Yu

llms computer-vision fine-tuning benchmarks

arXiv AI

Oct 15

4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling

arXiv:2610.17625v1 Announce Type: cross Abstract: For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated g...

By Jianhui Zhang, Zuyao Lin, Pengxin Xu, Jingdong Wang, Xingyu Chen

diffusion fine-tuning

arXiv AI

Oct 15

Auditing Failure Attribution: Label Predictability and Judge Behavior

arXiv:2610.17747v1 Announce Type: cross Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step agai...

By Tianyang Xu, Jing Gao

llms agents fine-tuning benchmarks

arXiv AI

Oct 15

Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages

arXiv:2610.18420v1 Announce Type: cross Abstract: We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English language model, from scratch on about 50 billion tokens (58% Tamil, the rest English, m...

By Ramchand Kumaresan, Madhusudhanan G, Kaushik Kezendirane

llms agents nlp fine-tuning benchmarks

arXiv AI

Oct 15

Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison

arXiv:2610.18415v1 Announce Type: cross Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment st...

By Pratuat Amatya, Vinay Setty, V Venktesh, Avishek Anand

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Oct 15

PhysicsSliders: Learning Physical Controls for Audio Foley Generation

arXiv:2610.18597v1 Announce Type: cross Abstract: Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictabl...

By Peiwei Chang, Yongqiang Chen, Yuelan Cheng, Liting Gao, Yishun Lu, Li Zhang, Mark D. Plumbley, Philip J. B. Jackson, Wenwu Wang

fine-tuning

arXiv AI

Oct 15

Geometric Calibration of Supervised Fine-Tuning

arXiv:2610.18634v1 Announce Type: cross Abstract: Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directio...

By Jianzhu Bao, Jia-Chen Gu, Qingyuan Liu, Haozhen Zhang, Kai-Wei Chang, Nanyun Peng, Wenya Wang

llms fine-tuning

arXiv AI

Oct 15

GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models

arXiv:2610.18694v1 Announce Type: cross Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models...

By Rong Li, Shijie Li, Jiangyong Huang, Lingdong Kong, Jiaming Zhou, Dongyue Lu, Zeying Gong, Baoxiong Jia, Junwei Liang, Siyuan Huang

llms nlp fine-tuning multimodal benchmarks safety

arXiv AI

Oct 15

CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Web Cloud-Edge Systems

arXiv:2606.00756v2 Announce Type: replace Abstract: LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency. However, the li...

By Yannan Wang, Longli Yang, Zhen Liu, Abhishek Kumar, Carsten Maple

llms agents fine-tuning benchmarks

arXiv AI

Oct 15

One Size Does Not Fit All: Distribution-Guided Tensor-Wise Adaptive Sparsification for Model Merging

arXiv:2508.06163v2 Announce Type: replace-cross Abstract: Merging multiple task-specific fine-tuned checkpoints into a single multi-task model provides an attractive alternative to joint multi-task t...

By Yingfeng Luo, Dingyang Lin, Junxin Wang, Kaiyan Chang, Ziqiang Xu, Weiqiao Shan, Yinqiao Li, Tong Zheng, Bei Li, Anxiang Ma, Tong Xiao, Zhengtao Yu, Jingbo Zhu

llms fine-tuning efficiency multimodal benchmarks

arXiv AI

Oct 15

GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models

arXiv:2601.07632v5 Announce Type: replace-cross Abstract: Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and m...

By Zhankai Ye, Bofan Li, Yukai Jin, Shuoqiu Li, Wei Wang, Yanfu Zhang, Shangqian Gao, Xin Liu

llms rag nlp fine-tuning efficiency safety

arXiv AI

Oct 15

Flow Policy Gradients for Robot Control

arXiv:2602.02481v2 Announce Type: replace-cross Abstract: Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on di...

By Brent Yi, Hongsuk Choi, Himanshu Gaurav Singh, Xiaoyu Huang, Takara E. Truong, Carmelo Sferrazza, Yi Ma, Rocky Duan, Pieter Abbeel, Guanya Shi, Karen Liu, Angjoo Kanazawa

diffusion reinforcement-learning robotics fine-tuning

arXiv AI

Oct 15

TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour

arXiv:2602.02331v2 Announce Type: replace-cross Abstract: Achieving highly dynamic parkour with humanoid robots on complex terrains unseen during the pre-training stage remains a challenge in robotic...

By Shaoting Zhu, Baijun Ye, Jiaxuan Wang, Jiakang Chen, Ziwen Zhuang, Linzhan Mou, Runhan Huang, Hang Zhao

robotics fine-tuning

arXiv AI

Oct 15

HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding

arXiv:2605.08158v2 Announce Type: replace-cross Abstract: Long video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB fr...

By Haopeng Jin, Wenlong Zhao, Tao Yu, Tiankun Yang, Zhenyu Guan, ShiQuan Dong, Yujia Yang, Shani Ye, Chubin Chen, Hongzhu Yi, Jinwen Luo

llms fine-tuning multimodal safety

arXiv Machine Learning

Oct 15

PairIT: Autoregressive Transformers for Low-Data Molecule Optimization

arXiv:2610.19123v1 Announce Type: new Abstract: Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation,...

By Hannah Lawrence, Bodhi P. Vani, Ji Won Park, Natasa Tagasovska, Samuel Don Stanton, Andrew Martin Watkins, Michael Maser, Ewa M. Nowara

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Oct 15

Scaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction

arXiv:2610.19015v1 Announce Type: new Abstract: Real measurements are too limited to train an accurate indoor pathloss predictor that works across a wide range of buildings. Large-scale synthetic pre...

By Khoren Petrosyan, Artashes Mkrtchyan, Rafayel Mkrtchyan, Hrant Khachatrian, Theofanis P. Raptis

fine-tuning benchmarks

arXiv Machine Learning

Oct 15

How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts

arXiv:2610.19033v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) applies every rank-one component of its update to every token, and mixture-of-experts variants replace this with a learned r...

By Mei Okonkwo, Owen Castellanos, Ingrid Solberg, Yusuf Demirel

llms fine-tuning

arXiv Machine Learning

Oct 15

LLMs program using Reusable and Composable Abstract Representations

arXiv:2610.19238v1 Announce Type: new Abstract: When writing code, the same computation can be expressed in different programming languages and through different implementation strategies. We show th...

By Casper L. Christensen, Kyle J. Ray, Dmitry Manning-Coe, Adam Shai, Paul Riechers

llms fine-tuning

Get the daily briefing