Fine-tuning and adaptation

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

3,943 stories · RSS feed

arXiv AI

Jun 9

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers

arXiv:2606. 07593v1 Announce Type: cross Abstract: The widespread use of image classification models in high-risk, real-world situations necessitates making these models robust to slight disturbances or perturbations, such as blurring or sharpening, in the input images.

By Hannah Gao (Massachusetts Institute of Technology), Isha Agarwal (Massachusetts Institute of Technology), Dylan Hadfield-Menell (Massachusetts Institute of Technology), Rachel Ma (Massachusetts Institute of Technology)

llms computer-vision fine-tuning multimodal safety

arXiv AI

Jun 9

Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline

arXiv:2606. 07965v1 Announce Type: new Abstract: Large Visual Language Models (LVLMs) have achieved remarkable success in vision tasks.

By Zekai Zhang, Qinghui Chen, Maomao Xiong, Shijiao Ding, Zhanzhi Su, Xinjie Yao, Yiming Sun, Cong Bai, Jinglin Zhang

llms fine-tuning multimodal benchmarks

arXiv AI

Jun 9

Proposal Refinement for Few-Shot Object Detection

arXiv:2606. 09245v1 Announce Type: cross Abstract: Few-shot object detection has gained widely attention in recent years.

By Yuan Zeng, Bin Song, Jie Guo, Yuwen Chen

computer-vision fine-tuning benchmarks

arXiv AI

Jun 9

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment

arXiv:2606. 08016v1 Announce Type: cross Abstract: Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes.

By Zichen Zhu, Yuheng Sun, Mingxuan Zhu, Wenjie Ma, Situo Zhang, Zhexiang Wang, Ziyue Yang, Danyang Zhang, Kunyao Lan, Zihan Zhao, Dingye Liu, Siqi Xiang, Lu Chen, Kai Yu

agents nlp fine-tuning safety

arXiv AI

Jun 9

Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

arXiv:2606. 08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs).

By Shi Ying Chang, Chiok Yew Ho, Yichen Li, Yintong Huo

llms fine-tuning

arXiv Machine Learning

Jun 9

Curvature-Guided LoRA: Matching Full Fine-Tuning in Function Space

arXiv:2603. 29824v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning methods such as LoRA enable efficient adaptation of large pretrained models, but often lag behind full fine-tuning in both convergence speed and final performance.

By Fr\'ed\'eric Zheng, Alexandre Prouti\`ere

fine-tuning benchmarks safety

arXiv AI

Jun 9

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.

By Omar Mahmoud, Aly M. Kassem, Thommen George Karimpanal, Buddhika Laknath Semage, Negar Rostamzadeh, Golnoosh Farnadi, Santu Rana

llms robotics fine-tuning benchmarks safety

arXiv Machine Learning

Jun 9

Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families

arXiv:2606. 09456v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has become a core technique in the post-training of Large Language Models (LLMs) for transferring knowledge from domain experts to student models.

By Yifan Niu, Han Xiao, Dongyi Liu, Zelong Wang, Dihong Gong, Yasheng Wang, Jia Li

llms nlp fine-tuning efficiency benchmarks

arXiv AI

Jun 9

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.

By Xinyu Guan, Qianyang Zhao, Yuming Deng

llms rag agents fine-tuning benchmarks

arXiv AI

Jun 9

ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies

arXiv:2606. 09630v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies provide strong priors for language-conditioned manipulation, but remain brittle in off-nominal states requiring targeted recovery.

By Haodi Hu, Chung-Ta Huang, Jing Liu, Ye Wang, Kei Suzuki, Matthew Brand, Toshiaki Koike-Akino

llms robotics fine-tuning multimodal

arXiv Machine Learning

Jun 9

From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning

arXiv:2606. 09092v1 Announce Type: new Abstract: Theory of Mind (ToM) is a must-acquire skill for modern foundation model systems to operate effectively and safely in the real world.

By Jike Zhong, Yuxiang Lai, Ming Li, Yuheng Li, Wuao Liu, Behzad Dariush, Konstantinos Psounis, Shao-Yuan Lo

reinforcement-learning fine-tuning multimodal

arXiv AI

Jun 9

Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models

arXiv:2606. 08446v1 Announce Type: cross Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive.

By Yang Zhou, Ranajoy Sadhukhan, Zhaofeng Sun, Zhuoming Chen, Souvik Kundu, Saket Dingliwal, Sai Muralidhar Jayanthi, Aram Galstyan, Haizhong Zheng, Beidi Chen

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Jun 9

A Mixed Diet Makes DINO An Omnivorous Vision Encoder

arXiv:2602. 24181v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks.

By Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson, Ye Xia, Skanda Koppula, Andre Araujo, Joao Carreira, Niloy J. Mitra

rag computer-vision fine-tuning efficiency multimodal safety

arXiv AI

Jun 9

Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design

arXiv:2606. 09266v1 Announce Type: cross Abstract: Acoustic metamaterial (AMM) inverse design is particularly challenging for broadband target responses due to acoustic dispersion: a structure that matches the desired response at one frequency may deviate at others, and modifying geometry to improve one sub-band often perturbs neighboring sub-bands.

By Yijie Li, Jiahao Xu, Ching-Chih Tsao, Lili Qiu, Jingxian Wang

reinforcement-learning fine-tuning

arXiv AI

Jun 9

Minibatch Selection via Partition Matroid Constrained Gradient Matching

arXiv:2606. 07954v1 Announce Type: cross Abstract: Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains.

By Prayas Agrawal, Prateek Chanda, Ishita Khatri, Ganesh Ramakrishnan, Bamdev Mishra, Pratik Jawanpuria

llms fine-tuning benchmarks

arXiv AI

Jun 9

Post-training is (Massive) Supervised Learning

arXiv:2606. 07527v1 Announce Type: cross Abstract: The prevailing paradigm for training LLMs has evolved to rely on a massive post-training phase consisting of SFT and RL.

By Michael Hassid, Yossi Adi, Roy Schwartz

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 9

Transfer learning for causal forest

arXiv:2606. 07693v1 Announce Type: cross Abstract: Transfer learning addresses the challenge of transfering knowledge from one domain to another.

By B\'er\'enice-Alexia Jocteur (ICJ, PSPM), V\'eronique Maume-Deschamps (ICJ, PSPM), Pierre Ribereau (PSPM, ICJ)

fine-tuning

arXiv AI

Jun 9

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation

arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).

By Qi Cao, Jian Lou, Meiting Liu, Wenjie Feng, Dan Li, See-Kiong Ng, Anh Tuan Luu

llms fine-tuning safety

arXiv AI

Jun 9

Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning

arXiv:2507. 12612v4 Announce Type: replace-cross Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks.

By Prateek Chanda, Saral Sureka, Parth Pratim Chatterjee, Krishnateja Killamsetty, Nikhil Shivakumar Nayak, Ganesh Ramakrishnan

llms fine-tuning

arXiv Machine Learning

Jun 9

Learning from flowsheets: A generative transformer model for autocompletion of flowsheets

arXiv:2208. 00859v2 Announce Type: replace Abstract: We propose a novel method enabling autocompletion of chemical flowsheets.

By Gabriel Vogel, Lukas Schulze Balhorn, Artur M. Schweidtmann

llms fine-tuning

Get the daily briefing