English
Related papers

Related papers: PYRA: Parallel Yielding Re-Activation for Training…

200 papers

Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the weight change, i.e.,…

Machine Learning · Computer Science 2024-05-07 Ziqi Gao , Qichao Wang , Aochuan Chen , Zijing Liu , Bingzhe Wu , Liang Chen , Jia Li

In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-29 Jin Lee , Zhonghao Chen , Xuhang He , Robert Underwood , Bogdan Nicolae , Franck Cappello , Xiaoyi Lu , Sheng Di , Zheng Zhang

Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we…

Machine Learning · Computer Science 2024-11-19 Haizhou Ge , Ruixiang Wang , Zhu-ang Xu , Hongrui Zhu , Ruichen Deng , Yuhang Dong , Zeyu Pang , Guyue Zhou , Junyu Zhang , Lu Shi

Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant…

Robotics · Computer Science 2025-12-11 Yifan Ye , Jiaqi Ma , Jun Cen , Zhihe Lu

Parameter-efficient fine-tuning (PEFT) methods have emerged as a practical solution for adapting large foundation models to downstream tasks, reducing computational and memory costs by updating only a small subset of parameters. Among them,…

Machine Learning · Computer Science 2025-12-30 Guoan Wan , Tianyu Chen , Fangzheng Feng , Haoyi Zhou , Runhua Xu

Large pre-trained speech models are widely used as the de-facto paradigm, especially in scenarios when there is a limited amount of labeled data available. However, finetuning all parameters from the self-supervised learned model can be…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-16 Nanxin Chen , Izhak Shafran , Yu Zhang , Chung-Cheng Chiu , Hagen Soltau , James Qin , Yonghui Wu

While Reinforcement Learning from Human Feedback (RLHF) effectively aligns pretrained Large Language and Vision-Language Models (LLMs, and VLMs) with human preferences, its computational cost and complexity hamper its wider adoption. To…

Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing terms, and initial conditions.…

Machine Learning · Computer Science 2025-06-30 Louis Serrano , Armand Kassaï Koupaï , Thomas X Wang , Pierre Erbacher , Patrick Gallinari

Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the…

Machine Learning · Computer Science 2025-09-19 Eric Nuertey Coleman , Luigi Quarantiello , Samrat Mukherjee , Julio Hurtado , Vincenzo Lomonaco

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Haiwen Diao , Bo Wan , Ying Zhang , Xu Jia , Huchuan Lu , Long Chen

Adapting Large Language Models (LLMs) to new tasks through fine-tuning has been made more efficient by the introduction of Parameter-Efficient Fine-Tuning (PEFT) techniques, such as LoRA. However, these methods often underperform compared…

Computation and Language · Computer Science 2024-05-24 Chunlin Tian , Zhan Shi , Zhijiang Guo , Li Li , Chengzhong Xu

Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Siqi Luo , Haoran Yang , Yi Xin , Mingyang Yi , Guangyang Wu , Guangtao Zhai , Xiaohong Liu

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

Machine Learning · Computer Science 2025-03-11 Yibo Yang , Xiaojie Li , Zhongzhu Zhou , Shuaiwen Leon Song , Jianlong Wu , Liqiang Nie , Bernard Ghanem

Modern Transformer-based models frequently suffer from miscalibration, producing overconfident predictions that do not reflect true empirical frequencies. This work investigates the calibration dynamics of LoRA: Low-Rank Adaptation and a…

Computation and Language · Computer Science 2026-03-31 Bartosz Trojan , Filip Gębala

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards…

Machine Learning · Computer Science 2026-05-20 Chengqian Zhang , Wei Zhu , Kyumin Lee

This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be…

Machine Learning · Computer Science 2022-07-20 Wenqi Shao , Xun Zhao , Yixiao Ge , Zhaoyang Zhang , Lei Yang , Xiaogang Wang , Ying Shan , Ping Luo

Reinforcement Learning (RL) struggles in problems with delayed rewards, and one approach is to segment the task into sub-tasks with incremental rewards. We propose a framework called Hierarchical Inverse Reinforcement Learning (HIRL), which…

Robotics · Computer Science 2016-04-25 Sanjay Krishnan , Animesh Garg , Richard Liaw , Lauren Miller , Florian T. Pokorny , Ken Goldberg

The performance of gradient-based optimization strategies depends heavily on the initial weights of the parametric model. Recent works show that there exist weight initializations from which optimization procedures can find the…

Machine Learning · Computer Science 2020-01-23 Rafael Rego Drumond , Lukas Brinkmeyer , Josif Grabocka , Lars Schmidt-Thieme

Recent advancements in Large Language Models (LLMs) have achieved robust performance across diverse tasks, but fine-tuning these models for specific domains remains resource-intensive. Parameter-Efficient Fine-Tuning (PEFT) methods like…

Computation and Language · Computer Science 2025-02-19 Yuxuan Zhang , Ruizhe Li

We propose TLoRA, a novel tri-matrix low-rank adaptation method that decomposes weight updates into three matrices: two fixed random matrices and one trainable matrix, combined with a learnable, layer-wise scaling factor. This tri-matrix…

Machine Learning · Computer Science 2025-12-02 Tanvir Islam