Fine-tuning and adaptation

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

8,205 stories · RSS feed

arXiv Machine Learning

Aug 18

Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface

arXiv:2608. 16134v1 Announce Type: new Abstract: In clinical motor imagery brain-computer interface (MI-BCI) decoding, cross-day transferability and online operation remain two critical challenges.

By Siqi Li (Peking University, Chinese Institute for Brain Research, Beijing), Zhi Li (NeuCyber Neurotech), Tong Liu (NeuCyber Neurotech), Shuai Zhang (NeuCyber Neurotech), Yanfei Jia (Beijing Medical University), Zhiqiang Yi (Beijing Medical University), Jue Xie (NeuCyber Neurotech), Ni Ji (Chinese Academy of Medical Sciences & Peking Union Medical College, Chinese Institute for Brain Research, Beijing)

fine-tuning benchmarks safety

arXiv Machine Learning

Aug 18

Towards a theory of inference-time alignment with unknown rewards

arXiv:2608. 15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation.

By Steve Hanneke, Hongao Wang, Mingyue Xu

fine-tuning safety

arXiv Machine Learning

Aug 18

UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity

arXiv:2608. 15516v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated strong performance in multimodal understanding and generation.

By Pengyu Wang, Baochen Xiong, Xiaoshan Yang, Yifan Xu, Zhang Qimeng, Haifeng Chen, Changsheng Xu

llms fine-tuning efficiency multimodal benchmarks safety

arXiv Machine Learning

Aug 18

Spectral Rank Certification for Foundation Model Adapters

arXiv:2608. 15351v1 Announce Type: new Abstract: Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity.

By Mohammed Ahnouch, Lotfi Elaachak

fine-tuning

arXiv Machine Learning

Aug 18

Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers

arXiv:2608. 14649v1 Announce Type: new Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification.

By Pawan Kumar

llms diffusion nlp fine-tuning

arXiv AI

Aug 18

Multimodal Language Models Benchmarked Against the NRC Reactor Operator Licensing Examination: Fine-Tuning and Retrieval Strategies

arXiv:2607. 22067v2 Announce Type: replace-cross Abstract: Competence claims for a language model in a safety-critical domain are credible when measured against a standard the domain already enforces.

By Isak Hwang, Yoon Pyo Lee, Syed Bahauddin Alam

llms rag fine-tuning multimodal safety

arXiv AI

Aug 18

Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis

arXiv:2511. 11439v3 Announce Type: replace-cross Abstract: Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics.

By Yiling He, Junchi Lei, Hongyu She, Shuo Shao, Xinran Zheng, Yiping Liu, Zhan Qin, Lorenzo Cavallaro

nlp fine-tuning

arXiv AI

Aug 18

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

arXiv:2603. 24575v2 Announce Type: replace-cross Abstract: Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability.

By Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Zhongzheng Ren, Daniel S Weld, Ranjay Krishna

llms rag reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Aug 18

mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA

arXiv:2411. 15041v2 Announce Type: replace Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and Encyclopedic-VQA, due to their limited and frozen knowledge scope, often leading to ambiguous and inaccurate responses.

By Tao Zhang, Ziqi Zhang, Zongyang Ma, Yuxin Chen, Zhongang Qi, Chunfeng Yuan, Bing Li, Junfu Pu, Yuxuan Zhao, Zehua Xie, Jin Ma, Ying Shan, Weiming Hu

llms rag nlp fine-tuning multimodal benchmarks

arXiv Machine Learning

Aug 18

Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

arXiv:2608. 14929v1 Announce Type: cross Abstract: Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented.

By Aman Singh Thakur, Rayan Khoury

llms fine-tuning efficiency benchmarks

arXiv AI

Aug 18

CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications

arXiv:2608. 15972v1 Announce Type: cross Abstract: Synchronized camera and wireless measurements observe the same scene through different physical channels.

By Yubo Zhang, Yiyao Liu

fine-tuning multimodal safety

arXiv AI

Aug 18

FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy

arXiv:2608. 15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specialized hardware kernels, thus failing to unleash the full acceleration potential due to persistent reliance on expensive floating-point arithmetic or runtime dequantization overheads.

By Qingyao Yang, Runming Yang, He Xiao, Wendong Xu, Junyu Chen, Haobo Liu, Chenchen Ding, Ruihan Hu, Yik-Chung Wu, Ngai Wong

llms fine-tuning efficiency

arXiv AI

Aug 18

SAPE: Sandwich Adapters for Parameter Efficiency in Large Language Model Fine-Tuning

arXiv:2608. 15360v1 Announce Type: cross Abstract: While Parameter-Efficient Fine-Tuning (PEFT) has substantially reduced the hardware cost of adapting Large Language Models (LLMs) by decreasing the number of trainable parameters, recent studies have sought to further improve PEFT through parameter sharing.

By Mohammad Aref Jafari-Raddani, Morteza Mohajjel Kafshdooz

llms rag fine-tuning benchmarks

arXiv AI

Aug 18

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

arXiv:2608. 15285v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temporally static updates throughout a control rollout, overlooking the phase-dependent nature of continuous-action manipulation.

By Yufei Guo, Yinan Wu, Haoran Duan, Guiguang Ding, Jungong Han

robotics fine-tuning multimodal

arXiv AI

Aug 18

Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection

arXiv:2608. 14675v1 Announce Type: cross Abstract: While Self-Supervised Learning (SSL) effectively extracts general representations from noisy, unconstrained physiological signals such as photoplethysmography (PPG), its suitability for highly subjective tasks remains unproven.

By Dominika Kunc, Przemys{\l}aw Kazienko, Stanis{\l}aw Saganowski

reinforcement-learning fine-tuning

arXiv AI

Aug 18

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization

arXiv:2602. 15983v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations---a feasibility--correctness gap reaching 90 percentage points on compositional problems.

By Junbo Jacob Lian, Yujun Sun, Huiling Chen, Chaoyu Zhang, Hanzhang Qin, Chung-Piaw Teo

llms fine-tuning benchmarks

arXiv AI

Aug 18

Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning

arXiv:2503. 09020v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been widely adopted in commercial code completion engines, significantly enhancing coding efficiency and productivity.

By Liang Lu, Yuan Jiang, Christoph Treude, Shuzheng Gao, Jingyu Xiao, Xiaohong Su, Michael R. Lyu

llms fine-tuning benchmarks

arXiv AI

Aug 18

Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label Sparsity

arXiv:2608. 16612v1 Announce Type: cross Abstract: An accurate estimation of the state of health (SOH) underpins a safe and optimized use of the battery system.

By Jiaqi Yao, Julia Kowal

fine-tuning efficiency

arXiv AI

Aug 18

Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation

arXiv:2608. 15949v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy and natural dialogue.

By Cedar Site Bai, Duanshun Li, Zhenyu Liao, Sheikh Sarwar, Huiyuan Chen, Yuan Chen, Changhe Yuan, Haiyang Zhang, Qilin Qi

llms agents reinforcement-learning fine-tuning

arXiv AI

Aug 18

MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration

arXiv:2601. 23049v2 Announce Type: replace Abstract: Medical calculators are fundamental to quantitative, evidence-based clinical practice.

By Yakun Zhu, Yutong Huang, Shengqian Qin, Zhongzhen Huang, Shaoting Zhang, Xiaofan Zhang

llms agents fine-tuning benchmarks data-engineering

Get the daily briefing