Fine-tuning and adaptation

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

8,248 stories · RSS feed

arXiv AI

Jun 3

SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model

arXiv:2603. 26738v3 Announce Type: replace-cross Abstract: While automated sleep staging has achieved expert-level accuracy, its clinical adoption is hindered by a lack of auditable reasoning.

By Guifeng Deng, Pan Wang, Mengfan Niu, Jiquan Wang, Shuying Rao, Junyi Xie, Xi'ang Chen, Sha Zhao, Gang Pan, Wanjun Guo, Tao Li, Haiteng Jiang

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 3

Patcher: Post-Hoc Patching of Backdoored Large Language Models

arXiv:2606. 02995v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms.

By Anjun Gao, Yueyang Quan, Yufei Xia, Zhuqing Liu, Minghong Fang

llms fine-tuning safety

arXiv AI

Jun 3

ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization

arXiv:2501. 17377v4 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) has emerged as a promising approach for solving Combinatorial Optimization (CO) problems, such as the 3D Bin Packing Problem (3D-BPP), Traveling Salesman Problem (TSP), or Vehicle Routing Problem (VRP), but these neural solvers often exhibit brittleness when facing distribution shifts.

By Han Fang, Paul Weng, Yutong Ban

reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 3

Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines

arXiv:2605. 25645v2 Announce Type: replace-cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation.

By Jatin Kishnani, Mayank Goel, Amit Singh, Pulkit Agrawal, Sairanjan Mishra

llms fine-tuning efficiency data-engineering

arXiv AI

Jun 3

Consistency Training Can Entrench Misalignment

arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.

By David Demitri Africa, Arathi Mani

fine-tuning safety

arXiv AI

Jun 3

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability

arXiv:2606. 03648v1 Announce Type: cross Abstract: Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety.

By Krishnapriya Vishnubhotla, Hillary Dawkins, Isar Nejadgholi, Svetlana Kiritchenko

llms fine-tuning benchmarks safety

arXiv AI

Jun 3

A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners

arXiv:2606. 03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and reason about the planning problems they are solving?

By Patrick Emami, Nan Qiang, Peter Graf

llms fine-tuning safety

arXiv AI

Jun 3

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

arXiv:2604. 18995v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction.

By Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin

llms diffusion fine-tuning efficiency

arXiv Machine Learning

Jun 3

ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models

arXiv:2511. 19959v2 Announce Type: replace Abstract: Federated learning (FL) has been extensively studied as a privacy-preserving training paradigm.

By Yujia Wang, Yuanpu Cao, Jinghui Chen

llms fine-tuning safety

arXiv AI

Jun 3

Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation

arXiv:2606. 03963v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks.

By Roohan Ahmed Khan, Yasheerah Yaqoot, Muhammad Ahsan Mustafa, Dzmitry Tsetserukou

llms agents reinforcement-learning robotics fine-tuning multimodal

arXiv Machine Learning

Jun 3

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks

arXiv:2606. 02947v1 Announce Type: new Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks.

By Ivan Saboli\'c, Marin Or\v{s}i\'c, Josip \v{S}ari\'c, Sven Lon\v{c}ari\'c

llms fine-tuning multimodal

arXiv AI

Jun 3

BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language

arXiv:2606. 03504v1 Announce Type: cross Abstract: We present BaltiVoice, a 16.

By Muhammad Ali

fine-tuning multimodal

arXiv AI

Jun 3

Pretraining Language Models on Historical Text

arXiv:2606. 02991v1 Announce Type: cross Abstract: We introduce TypewriterLM, a 7.

By Xiaoxi Luo, Zachary Shinnick, Niclas Griesshaber, Yixuan Wang, Junchi Yu, Freda Shi, Philip Torr, Yao Lu

llms fine-tuning benchmarks data-engineering

arXiv AI

Jun 3

Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution

arXiv:2505. 24037v3 Announce Type: replace Abstract: Sparse large language models (LLMs) offer an attractive direction toward efficient deployment, but adapting them to downstream tasks remains challenging.

By Qiao Xiao, Alan Ansell, Boqian Wu, Lu Yin, Mykola Pechenizkiy, Shiwei Liu, Decebal Constantin Mocanu

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 3

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter

arXiv:2606. 03723v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapters, complicating reuse and deployment.

By Zhengbao He, Ruiqi Ding, Zhehao Huang, Ruikai Yang, Tao Li, Xiaolin Huang

fine-tuning

arXiv AI

Jun 3

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation

arXiv:2606. 03385v1 Announce Type: cross Abstract: In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error.

By Jiahao Xu, Peiyuan Wang, Hanzhuo Zhang, Zihao Yu, Tianyu Fu, Hao Chen, Xuanhao Xiang, Jianbo Yu, Chenchen Fu, Wanyuan Wang

diffusion reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Jun 3

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion

arXiv:2606. 03441v1 Announce Type: cross Abstract: Autonomous vision-based perching of quadrotors on moving inclined platforms is critical for air-ground collaboration but remains challenging due to the limited field of view (FOV).

By Zihong Lu, Zongzhuo Liu, Huaxu Li, Jinqiang Cui, Jie Mei, Youmin Gong, U Kei Cheang, Boyu Zhou

agents reinforcement-learning fine-tuning

arXiv AI

Jun 3

Multiple Choice Learning of Low-Rank Adapters for Language Modeling

arXiv:2507. 10419v3 Announce Type: replace-cross Abstract: We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausible sentence continuations at inference time.

By Victor Letzelter, Hugo Malard, Mathieu Fontaine, Ga\"el Richard, Slim Essid, Andrei Bursuc, Patrick P\'erez

llms nlp fine-tuning

arXiv Machine Learning

Jun 3

HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models

arXiv:2606. 03131v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking.

By Shuang Liu, Yuxuan Bo, Qiuyang Zhao, Caiyue Huang, Xiaorong Chen, Yanguang Liu, Mengnan Du

llms reinforcement-learning fine-tuning safety

arXiv AI

Jun 3

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

arXiv:2606. 03489v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data.

By Wenqi Chen, Ziyan Zhang, Bing Wang, Lin Liu, Hengheng Zhang, Zhengsu Chen

llms reinforcement-learning fine-tuning benchmarks safety

Get the daily briefing