Fine-tuning and adaptation

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

3,511 stories · RSS feed

arXiv Machine Learning

Jul 15

When Directional Accuracy Lies: A Base-Rate-Honest Benchmark for LoRA-Adapted TimesFM on Equity Forecasting

arXiv:2607. 12248v1 Announce Type: cross Abstract: Large pretrained time-series models such as TimesFM are attractive for financial forecasting, but raw directional accuracy is a misleading scoreboard in equity markets.

By Taizhen Cheung, SA Kwon

fine-tuning benchmarks

arXiv Machine Learning

Jul 15

APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model

arXiv:2603. 08862v2 Announce Type: replace-cross Abstract: Autonomous navigation in highly constrained environments remains challenging for mobile robots.

By Yuanjie Lu, Beichen Wang, Zhengqi Wu, Yang Li, Xiaomin Lin, Chengzhi Mao, Xuesu Xiao

llms agents reinforcement-learning robotics fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 15

When Close Enough Is Not Enough: Autoregressive Drift in Quantum Circuit Synthesis

arXiv:2607. 12780v1 Announce Type: cross Abstract: Quantum circuit optimization for fault-tolerant computing requires exact functional equivalence while minimizing expensive non-Clifford resources such as T gates.

By Mehdi Saeedi, Eddie Richter, Paul Hartke

llms nlp fine-tuning

arXiv AI

Jul 15

Graph-Constrained Policy Learning for Extreme Clinical Code Prediction

arXiv:2607. 11954v1 Announce Type: cross Abstract: Clinical code prediction maps unstructured discharge summaries to ICD-10-CM leaf codes in a large, sparse, and deeply hierarchical label space.

By Amritpal Singh, Sebastian Torres, Khawar Shakeel, Syed Ahmad Chan Bukhari

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 15

RAFP: Identifying LLM Lineages via Rare-Region Fingerprints

arXiv:2505. 12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly released under restricted licenses, creating a growing need for robust model ownership verification.

By Yun-Yun Tsai, Jia Hao Liang, Chuan Guo, Junfeng Yang, Laurens van der Maaten

llms fine-tuning efficiency safety

arXiv AI

Jul 15

Do You Remember? Toward Memory-Centric Multimodal AI

arXiv:2607. 11919v1 Announce Type: cross Abstract: Human memory is reconstructive, not a faithful recording.

By Xuguang Yu, Weigang Zheng, Minyue Yu

llms diffusion fine-tuning efficiency multimodal safety

arXiv Machine Learning

Jul 15

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

arXiv:2607. 12464v1 Announce Type: cross Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task.

By Jeeyung Kim, Erfan Esmaeili, Qiang Qiu

diffusion computer-vision reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 15

Scaling Point-in-Time Language Models

arXiv:2607. 11889v1 Announce Type: cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences.

By Bryan Kelly, Semyon Malamud, Johannes Schwab, Teng Andrea Xu

llms fine-tuning benchmarks safety

arXiv AI

Jul 15

Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering

arXiv:2603. 28583v2 Announce Type: replace-cross Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations.

By Yanjie Zhang, Yafei Li, Rui Sheng, Zixin Chen, Yanna Lin, Huamin Qu, Lei Chen, Yushi Sun

llms agents computer-vision nlp fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 15

Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs

arXiv:2607. 11997v1 Announce Type: cross Abstract: Multi-task model merging combines separately trained expert models into a single model that handles all tasks without co-training.

By Nikita Kozodoi, Zainab Afolabi, Jack Butler

llms fine-tuning safety

arXiv AI

Jul 15

From Reconstruction to Interpretation: Zero-Setup Multi-Phase Segmentation of X-ray Tomography Data

arXiv:2607. 12175v1 Announce Type: cross Abstract: X-ray tomography enables nondestructive characterization of material microstructures, while advances in micro-CT imaging have accelerated volumetric data acquisition and reconstruction.

By Pradyumna Elavarthi, Arun J. Bhattacharjee, Harrison Lisabeth, Anca Ralescu, Petrus H. Zwart, Dilworth Parkinson, Elizabeth G. Clark

llms computer-vision fine-tuning

arXiv AI

Jul 15

Accepted Prefixes Are Not All You Need: A Negative Result on PEFT-Based Block-Diffusion Drafting

arXiv:2607. 12422v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive language model inference by using a cheap drafter to propose multiple future tokens and a target model to verify them.

By Abdurrahman Javat, Allan Kazakov

llms diffusion nlp fine-tuning

arXiv AI

Jul 15

I'm Sorry, but I Can't Help with Braille: Revealing Accessibility Failures in State-of-the-Art LLMs

arXiv:2607. 11893v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform strongly on many language tasks, but their capability in structurally constrained, accessibility-critical modalities such as Braille remains unclear.

By Abdullah Abdullah

llms nlp fine-tuning benchmarks safety

arXiv AI

Jul 15

ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing

arXiv:2603. 24787v2 Announce Type: replace Abstract: Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models.

By Yaopei Zeng, Congchao Wang, Blake JianHang Chen, Lu Lin

llms fine-tuning multimodal

arXiv AI

Jul 15

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

arXiv:2605. 05686v3 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM).

By Qiyao Liang, Risto Miikkulainen, Ila Fiete

llms fine-tuning safety

arXiv AI

Jul 15

From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation

arXiv:2607. 12687v1 Announce Type: cross Abstract: LLMs can perform language-based quantitative prediction from unstructured inputs, but remain susceptible to hallucinations and overconfident errors, making it critical to know not only what a model predicts, but when its predictions can be trusted.

By Mehak Dhaliwal, Rasta Tadayon, Andong Hua, Haewon Jeong, Yao Qin

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 15

Explainable-by-Design Audio Deepfake Detection via Wiener-Hopf Linear Prediction

arXiv:2607. 12584v1 Announce Type: cross Abstract: The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics.

By Mattia Tamiazzo, Simone Milani, Massimo Iuliani, Marco Fontani

fine-tuning benchmarks safety

arXiv AI

Jul 15

The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning

arXiv:2607. 12177v1 Announce Type: new Abstract: The analysis of satellite and aerial imagery has entered a new era with the advent of foundation models.

By Shelley Cazares

llms agents fine-tuning multimodal benchmarks

arXiv AI

Jul 15

PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs

arXiv:2607. 12111v1 Announce Type: cross Abstract: Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges.

By Jing Liu, Kun Yang, Yan Wang, Dingkang Yang, Xiaoshuai Hao, Wei Zhang, Yang Liu, Wei Zhou

llms agents fine-tuning multimodal benchmarks safety

arXiv AI

Jul 15

Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning

arXiv:2509. 24372v3 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment.

By Xin Qiu, Yulu Gan, Conor F. Hayes, Qiyao Liang, Yinggan Xu, Roberto Dailey, Elliot Meyerson, Babak Hodjat, Risto Miikkulainen

llms reinforcement-learning fine-tuning benchmarks

Get the daily briefing