English
Related papers

Related papers: Iterative Finetuning is Mostly Idempotent

200 papers

Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning…

Machine Learning · Computer Science 2024-04-10 Aleksandar Petrov , Philip H. S. Torr , Adel Bibi

Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is not memorization itself, but its target: vanilla SFT drives…

Machine Learning · Computer Science 2026-05-26 Ruiying Peng , Mengyu Yang , Jing Lei , Xiaohui Li , Xueyu Wu , Xinlei Chen

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine…

Computation and Language · Computer Science 2022-10-28 Weiyan Shi , Ryan Shea , Si Chen , Chiyuan Zhang , Ruoxi Jia , Zhou Yu

Differentially Private Federated Learning (DPFL) strengthens privacy protection by perturbing model gradients with noise, though at the cost of reduced accuracy. Although prior empirical studies indicate that initializing from pre-trained…

Machine Learning · Computer Science 2025-10-10 Huitong Jin , Yipeng Zhou , Quan Z. Sheng , Shiting Wen , Laizhong Cui

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

As discussed in previous studies, the efficacy of evolutionary or reinforcement learning algorithms for continuous control optimization can be enhanced by including a neural module dedicated to feature extraction trained through…

Machine Learning · Computer Science 2021-06-09 Nicola Milano , Stefano Nolfi

Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often induce the "seesaw effect": optimizing for one task may…

Computation and Language · Computer Science 2026-01-27 Xiaoyu Liu , Xiaoyu Guan , Di Liang , Xianjie Wu

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

Machine Learning · Computer Science 2021-03-29 Dafni Antotsiou , Carlo Ciliberto , Tae-Kyun Kim

Face anti-spoofing aims to discriminate the spoofing face images (e.g., printed photos) from live ones. However, adversarial examples greatly challenge its credibility, where adding some perturbation noise can easily change the predictions.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-03 Songlin Yang , Wei Wang , Chenye Xu , Ziwen He , Bo Peng , Jing Dong

Large-scale foundation models have demonstrated remarkable versatility across a wide range of downstream tasks. However, fully fine-tuning these models incurs prohibitive computational costs, motivating the development of…

Machine Learning · Computer Science 2025-05-30 Chongjie Si , Xuankun Yang , Muqing Liu , Yadao Wang , Xiaokang Yang , Wenbo Su , Bo Zheng , Wei Shen

Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Nuoyan Zhou , Dawei Zhou , Decheng Liu , Nannan Wang , Xinbo Gao

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternative is Direct Policy Optimization (DPO), which replaces an…

Computation and Language · Computer Science 2024-06-03 Runsheng Yu , Yong Wang , Xiaoqi Jiao , Youzhi Zhang , James T. Kwok

Neural networks are often trained on multiple tasks, either simultaneously (multi-task learning, MTL) or sequentially (pretraining and subsequent finetuning, PT+FT). In particular, it is common practice to pretrain neural networks on a…

Machine Learning · Computer Science 2024-11-04 Samuel Lippl , Jack W. Lindsey

What are the limits of controlling language models via synthetic training data? We develop a reinforcement learning (RL) primitive, the Dataset Policy Gradient (DPG), which can precisely optimize synthetic data generators to produce a…

Computation and Language · Computer Science 2026-04-10 Tristan Thrush , Sung Min Park , Herman Brunborg , Luke Bailey , Marcel Roed , Neil Band , Christopher Potts , Tatsunori Hashimoto

Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained…

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

Current camera image and signal processing pipelines (ISPs), including deep-trained versions, tend to apply a single filter that is uniformly applied to the entire image. This is despite the fact that most acquired camera images have…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Chandrajit Bajaj , Yi Wang , Yunhao Yang

Upon the discovery of adversarial attacks, robust models have become obligatory for deep learning-based systems. Adversarial training with first-order attacks has been one of the most effective defenses against adversarial perturbations to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Inci M. Baytas , Debayan Deb

Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement, for example, by reconstructing datasets with refined…

Computation and Language · Computer Science 2025-10-28 Yongcheng Zeng , Xinyu Cui , Xuanfa Jin , Qirui Mi , Guoqing Liu , Zexu Sun , Mengyue Yang , Dong Li , Weiyu Ma , Ning Yang , Jian Zhao , Jianye Hao , Haifeng Zhang , Jun Wang
‹ Prev 1 8 9 10 Next ›