English
Related papers

Related papers: Logits Replay + MoClip: Stabilized, Low-Cost Post-…

200 papers

Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works have begun to close this gap by improving supervision quality,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Deen Dayal Mohan , Hossein Souri , Vitali Petsiuk , Juhong Min , Gopal Sharma , Luowei Zhou , Suren Kumar

Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as ICL demonstrations increase from a few to many, performance tends to plateau and eventually decline. We identify two…

Machine Learning · Computer Science 2025-05-28 Xiaoqing Zhang , Ang Lv , Yuhan Liu , Flood Sung , Wei Liu , Jian Luan , Shuo Shang , Xiuying Chen , Rui Yan

Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Reza Akbarian Bafghi , Carden Bagwell , Avinash Ravichandran , Ashish Shrivastava , Maziar Raissi

While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…

Computation and Language · Computer Science 2025-05-28 Jinwu Hu , Zhitian Zhang , Guohao Chen , Xutao Wen , Chao Shuai , Wei Luo , Bin Xiao , Yuanqing Li , Mingkui Tan

Training stability of large language models(LLMs) is an important research topic. Reproducing training instabilities can be costly, so we use a small language model with 830M parameters and experiment with higher learning rates to force…

Computation and Language · Computer Science 2024-10-23 Oleg Rybakov , Mike Chrzanowski , Peter Dykas , Jinze Xue , Ben Lanir

Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed augmentations, which…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Yuqing Lei , Yingjun Du , Yawen Huang , Xiantong Zhen , Ling Shao

Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain downstream datasets. Test-time adaptation (TTA) mitigates this issue by adjusting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Zixin Wang , Dong Gong , Sen Wang , Zi Huang , Yadan Luo

Aiming towards a holistic understanding of multiple downstream tasks simultaneously, there is a need for extracting features with better transferability. Though many latest self-supervised pre-training methods have achieved impressive…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Xiwen Liang , Yangxin Wu , Jianhua Han , Hang Xu , Chunjing Xu , Xiaodan Liang

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data…

Machine Learning · Computer Science 2023-03-08 Stella Ho , Ming Liu , Lan Du , Longxiang Gao , Yong Xiang

Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applications. This paper systematically investigates domain…

Computation and Language · Computer Science 2025-08-28 Daixuan Cheng , Shaohan Huang , Ziyu Zhu , Xintong Zhang , Wayne Xin Zhao , Zhongzhi Luan , Bo Dai , Zhenliang Zhang

Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet…

Computation and Language · Computer Science 2025-08-15 Jim Dilkes , Vahid Yazdanpanah , Sebastian Stein

Pretraining datasets for large language models (LLMs) have grown to trillions of tokens composed of large amounts of CommonCrawl (CC) web scrape along with smaller, domain-specific datasets. It is expensive to understand the impact of these…

Machine Learning · Computer Science 2024-06-06 Cody Blakeney , Mansheej Paul , Brett W. Larsen , Sean Owen , Jonathan Frankle

Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore…

Computation and Language · Computer Science 2024-10-22 Chengzhengxu Li , Xiaoming Liu , Zhaohan Zhang , Yichen Wang , Chen Liu , Yu Lan , Chao Shen

Existing studies of training state-of-the-art Contrastive Language-Image Pretraining (CLIP) models on large-scale data involve hundreds of or even thousands of GPUs due to the requirement of a large batch size. However, such a large amount…

Machine Learning · Computer Science 2024-10-03 Xiyuan Wei , Fanjiang Ye , Ori Yonay , Xingyu Chen , Baixi Sun , Dingwen Tao , Tianbao Yang

Continual learning requires the model to maintain the learned knowledge while learning from a non-i.i.d data stream continually. Due to the single-pass training setting, online continual learning is very challenging, but it is closer to the…

Machine Learning · Computer Science 2022-05-20 Gehui Shen , Shibo Jie , Ziheng Li , Zhi-Hong Deng

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Muhammad Uzair Khattak , Hanoona Rasheed , Muhammad Maaz , Salman Khan , Fahad Shahbaz Khan

To reduce user costs and maximize cluster utilization, large model training increasingly leverages volatile but inexpensive GPU capacity, such as spot instances and reclaimable resources in shared clusters. Yet, capitalizing on these…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-22 Haoyuan Liu , Kairui Zhou , Shuyao Qi , Qinwei Yang , Shengkai Lin , Shizhen Zhao , Wei Zhang

We introduce CompAct, a technique that reduces peak memory utilization on GPU by 25-30% for pretraining and 50% for fine-tuning of LLMs. Peak device memory is a major limiting factor in training LLMs, with various recent works aiming to…

Machine Learning · Computer Science 2025-02-11 Yara Shamshoum , Nitzan Hodos , Yuval Sieradzki , Assaf Schuster

In the past few years, large-scale pre-trained vision-language models like CLIP have achieved tremendous success in various fields. Naturally, how to transfer the rich knowledge in such huge pre-trained models to downstream tasks and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Tianxiang Hao , Xiaohan Ding , Juexiao Feng , Yuhong Yang , Hui Chen , Guiguang Ding

Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-21 Hanmei Yang , Jin Zhou , Yao Fu , Xiaoqun Wang , Ramine Roane , Hui Guan , Tongping Liu