English
Related papers

Related papers: AdapterTune: Zero-Initialized Low-Rank Adapters fo…

200 papers

Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…

Machine Learning · Computer Science 2023-07-04 Gal Kaplun , Andrey Gurevich , Tal Swisa , Mazor David , Shai Shalev-Shwartz , Eran Malach

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine Learning · Computer Science 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of…

Computation and Language · Computer Science 2021-07-14 Hang Le , Juan Pino , Changhan Wang , Jiatao Gu , Didier Schwab , Laurent Besacier

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Computation and Language · Computer Science 2024-02-27 Zekun Wang , Jingchang Chen , Wangchunshu Zhou , Haichao Zhu , Jiafeng Liang , Liping Shan , Ming Liu , Dongliang Xu , Qing Yang , Bing Qin

Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a…

Machine Learning · Computer Science 2026-05-12 Duong Nguyen , Mohammed Jawhar , Nicolas Chesneau

Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as a discrete…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Salim Khazem , Ibrahim Mohamed Serouis , Zakaria Ezzahed

Most calibration methods operate at the logit level, implicitly assuming that miscalibration can be corrected without changing the underlying representation. We challenge this assumption and propose \textbf{Calibration Attention (CalAttn)},…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Wenhao Liang , Wei Emma Zhang , Lin Yue , Miao Xu , Mingyu Guo , Olaf Maennel , Weitong Chen

The task of Few-shot Learning (FSL) aims to do the inference on novel categories containing only few labeled examples, with the help of knowledge learned from base categories containing abundant labeled training samples. While there are…

Computer Vision and Pattern Recognition · Computer Science 2023-01-09 Chengming Xu , Siqian Yang , Yabiao Wang , Zhanxiong Wang , Yanwei Fu , Xiangyang Xue

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-04 Mufan Sang , John H. L. Hansen

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples,…

Parameter-efficient fine-tuning (PEFT) methods face a tradeoff between adapter size and expressivity: ultra-low-parameter adapters are confined to fixed low-rank subspaces, capping performance even with extended training. We propose…

Machine Learning · Computer Science 2026-05-01 Raviteja Anantha , Nick Levato , Layne C. Price

Photonic computing has emerged as a promising substrate for accelerating the dense linear-algebra operations at the heart of AI, yet adoption for large Transformer models remains in its infancy. We identify two bottlenecks: (1) costly…

Emerging Technologies · Computer Science 2025-10-03 Hanqing Zhu , Zhican Zhou , Shupeng Ning , Xuhao Wu , Ray Chen , Yating Wan , David Pan

Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption remains limited due to heterogeneous preprocessing pipelines,…

Machine Learning · Computer Science 2025-12-03 Aditya Tanna , Pratinav Seth , Mohamed Bouadi , Utsav Avaiya , Vinay Kumar Sankarapu

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Computation and Language · Computer Science 2022-07-01 Jingping Liu , Yuqiu Song , Kui Xue , Hongli Sun , Chao Wang , Lihan Chen , Haiyun Jiang , Jiaqing Liang , Tong Ruan

Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive interaction data, limiting practical deployment. A common remedy is to leverage priors, such as…

Machine Learning · Computer Science 2025-09-29 Bumgeun Park , Donghwan Lee

Neural machine translation often adopts the fine-tuning approach to adapt to specific domains. However, nonrestricted fine-tuning can easily degrade on the general domain and over-fit to the target domain. To mitigate the issue, we propose…

Computation and Language · Computer Science 2021-03-29 Jianze Liang , Chengqi Zhao , Mingxuan Wang , Xipeng Qiu , Lei Li

Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising approach for improving frozen LLMs via interpretable interventions.…

Computation and Language · Computer Science 2026-02-12 Feijiang Han , Xiaodong Yu , Jianheng Tang , Delip Rao , Weihua Du , Lyle Ungar

Adapter-based fine-tuning has gained remarkable attention in adapting large pre-trained vision language models (VLMs) for a wide range of downstream tasks efficiently. In this paradigm, only the inserted adapters are fine-tuned, without the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Ying Huang , Yuanbin Man , Wenqi Jia , Zhengzhong Tu , Junzhou Huang , Miao Yin

Modern healthcare often utilises radiographic images alongside textual reports for diagnostics, encouraging the use of Vision-Language Self-Supervised Learning (VL-SSL) with large pre-trained models to learn versatile medical vision…

Computer Vision and Pattern Recognition · Computer Science 2024-01-03 Jiuming Qin , Che Liu , Sibo Cheng , Yike Guo , Rossella Arcucci