Fine-tuning and adaptation

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

3,721 stories · RSS feed

arXiv AI

Jul 3

World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments

arXiv:2607. 01470v1 Announce Type: new Abstract: Clinical protocol-execution tasks -- checking a lab value, applying a threshold, placing a correctly structured FHIR order -- are natural candidates for RL from world feedback: once clinical SMEs encode decision logic into a verifier, that verifier grades unlimited rollouts without per-episode annotation.

By Ananya Mantravadi, Harshit Rajgarhia, Prasanna Desikan, Abhishek Mukherji

agents reinforcement-learning fine-tuning

arXiv AI

Jul 3

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

arXiv:2607. 02010v1 Announce Type: new Abstract: Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time.

By Qianyu Chen, Ziteng Feng, Canran Xiao, Runxuan Tang

llms fine-tuning multimodal

arXiv AI

Jul 3

CLAP: Closed-Loop Training, Evaluation, and Release Control for Domain Agent Post-training

arXiv:2607. 01846v1 Announce Type: new Abstract: Domain agents often face noisy business data, uncertain post-training gains, offline/application mismatch, and adapter-release risk.

By Fangfei Li, Chenyang Zhao, Long Wang, Feng Tian, Zhiyue Zheng, Lv Guo

rag agents fine-tuning safety

arXiv AI

Jul 3

Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing

arXiv:2607. 01690v1 Announce Type: new Abstract: Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core claims, an effect known as Negation Neglect.

By Joshua Penman

llms fine-tuning safety

arXiv Machine Learning

Jul 3

Recursive Models for Long-Horizon Reasoning

arXiv:2603. 02112v2 Announce Type: replace Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning.

By Chenxiao Yang, Nathan Srebro, Zhiyuan Li

llms agents nlp fine-tuning

arXiv AI

Jul 3

ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models

arXiv:2512. 07843v2 Announce Type: replace-cross Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process.

By Long Lian, Sida Wang, Felix Juefei-Xu, Tsu-Jui Fu, Xiuyu Li, Adam Yala, Trevor Darrell, Alane Suhr, Yuandong Tian, Xi Victoria Lin

llms reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Jul 3

Episodic-to-Semantic Consolidation Without Identity Drift

arXiv:2607. 01988v1 Announce Type: new Abstract: Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity.

By Xue Qin, Simin Luan, Cong Yang, Zhijun Li

agents robotics fine-tuning

arXiv Machine Learning

Jul 3

QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs

arXiv:2602. 10431v4 Announce Type: replace Abstract: Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment.

By Kanghyun Noh, Jinheon Choi, Yulhwa Kim

llms fine-tuning efficiency benchmarks

arXiv AI

Jul 3

Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction

arXiv:2607. 01764v1 Announce Type: new Abstract: Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path, construct a proof-of-conceptv(PoC), and verify that the crash disappears on the patched build.

By Mingzhe Du, Luu Anh Tuan, Tianyi Wu, Renyang Liu, Zhijiang Guo, Dong Huang, See-Kiong Ng

llms agents fine-tuning

arXiv Machine Learning

Jul 3

On the Asymptotics of Self-Supervised Pre-training: Two-Stage M-Estimation and Representation Symmetry

arXiv:2603. 27631v2 Announce Type: replace Abstract: Self-supervised pre-training, where large corpora of unlabeled data are used to learn representations for downstream fine-tuning, has become a cornerstone of modern machine learning.

By Mohammad Tinati, Stephen Tu

fine-tuning

arXiv Machine Learning

Jul 3

Scaling to Multimodal and Multichannel Heart Sound Classification with Synthetic and Augmented Biosignals

arXiv:2509. 11606v4 Announce Type: replace-cross Abstract: Cardiovascular diseases (CVDs) are the leading cause of death worldwide, accounting for approximately 17.

By Milan Marocchi, Matthew Fynn, Kayapanda Mandana, Yue Rong

llms diffusion fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 3

LLM Priors for ERM over Programs

arXiv:2510. 14331v3 Announce Type: replace Abstract: We study program-learning methods that are efficient in both samples and computation.

By Shivam Singhal, Priyadarsi Mishra, Eran Malach, Tomer Galanti

llms fine-tuning

arXiv Machine Learning

Jul 3

One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective

arXiv:2607. 02292v1 Announce Type: new Abstract: Neural quantum states (NQS) provide a flexible and scalable framework for approximating quantum many-body wavefunctions.

By Juan Agust\'in Duque, Sergio Garc\'ia Heredia, Vinicius Hernandes, Eli\v{s}ka Greplov\'a, Thomas Spriggs, Aaron Courville, Anna Dawid

reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 3

WARP: Weight-Space Analysis for Recovering Training Data Portfolios

arXiv:2607. 01686v1 Announce Type: new Abstract: Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how different sources are sampled -- are rarely disclosed.

By Tzu-Heng Huang, Aditya Goyal, John Cooper, Frederic Sala

llms fine-tuning

arXiv Machine Learning

Jul 3

Hybrid quantum-classical neural network for sentiment analysis

arXiv:2607. 01943v1 Announce Type: new Abstract: Quantum machine learning has recently emerged as a promising paradigm that leverages the expressive power of quantum circuits to address complex learning tasks.

By Giacomo Cappiello, Filippo Caruso, Xing Liang, Dimitrios Makris

nlp fine-tuning

arXiv AI

Jul 3

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens

arXiv:2507. 02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable and sustainable.

By Salahuddin Salahuddin, Ahmed Hussain, Jussi L\"opp\"onen, Toni Jutila

llms fine-tuning benchmarks

arXiv AI

Jul 3

Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space

arXiv:2607. 01689v1 Announce Type: cross Abstract: Model merging aims to combine existing single-task solutions into a multi-task solution without additional data-driven fine-tuning.

By Long Minh Bui, Tuan Anh Le Van, Tung Phi Duc, Phi Le Nguyen, Jana Doppa, Trong Nghia Hoang

fine-tuning

arXiv AI

Jul 3

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

arXiv:2607. 02020v1 Announce Type: new Abstract: Multimodal large language models must continually adapt to evolving tasks and domains, yet standard continual learning metrics mainly measure whether old answers remain correct, leaving the stability of multimodal grounding largely unexamined.

By Qianyu Chen, Canran Xiao, Runxuan Tang

llms computer-vision fine-tuning multimodal

arXiv Machine Learning

Jul 3

BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer

arXiv:2607. 01410v1 Announce Type: cross Abstract: Sim2real transfer for robot policy learning suffers due to mismatch between simulation and reality.

By Yunfu Deng, Josiah P. Hanna

robotics fine-tuning

arXiv Machine Learning

Jul 3

Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

arXiv:2607. 01918v1 Announce Type: new Abstract: We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning.

By Yisong Fu, Zezhi Shao, Chengqing Yu, Yujie Li, Yongjun Xu, Xueqi Cheng, Fei Wang

llms nlp fine-tuning

Get the daily briefing