English
Related papers

Related papers: CoCoA-Mix: Confusion-and-Confidence-Aware Mixture …

200 papers

The in-context learning capabilities of modern language models have motivated a deeper mathematical understanding of sequence models. A line of recent work has shown that linear attention models can emulate projected gradient descent…

Computation and Language · Computer Science 2025-03-06 Xiangyu Chang , Yingcong Li , Muti Kara , Samet Oymak , Amit K. Roy-Chowdhury

Large Language Models (LLMs) are highly sensitive to prompt design, and making optimized prompting techniques is crucial for generating consistent, high-quality outputs. In this study, we introduce COSTAR-A, a novel prompt engineering…

Computation and Language · Computer Science 2025-10-15 Nzubechukwu C. Ohalete , Kevin B. Gittner , Lauren M. Matheny

Prompt tuning adapts Vision-Language Models like CLIP to open-world tasks with minimal training costs. In this direction, one typical paradigm evaluates model performance separately on known classes (i.e., base domain) and unseen classes…

Machine Learning · Computer Science 2025-05-09 Cong Hua , Qianqian Xu , Zhiyong Yang , Zitai Wang , Shilong Bao , Qingming Huang

Pre-trained models have been shown effective in many code intelligence tasks. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks…

Software Engineering · Computer Science 2022-07-26 Chaozheng Wang , Yuanhang Yang , Cuiyun Gao , Yun Peng , Hongyu Zhang , Michael R. Lyu

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ghada Sokar , Gintare Karolina Dziugaite , Anurag Arnab , Ahmet Iscen , Pablo Samuel Castro , Cordelia Schmid

Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform. Existing methods typically detour the problem by i) adjusting a loss function, ii) decoupling…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Youngseok Yoon , Sangwoo Hong , Hyungjun Joo , Yao Qin , Haewon Jeong , Jungwoo Lee

Image-text contrastive models such as CLIP learn transferable and robust representations for zero-shot transfer to a variety of downstream tasks. However, to obtain strong downstream performances, prompts need to be carefully curated, which…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Soumya Suvra Ghosal , Samyadeep Basu , Soheil Feizi , Dinesh Manocha

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…

Information Retrieval · Computer Science 2021-08-13 Luyu Gao , Jamie Callan

Molecular dynamics simulations have emerged as a fundamental instrument for studying biomolecules. At the same time, it is desirable to perform simulations of a collection of particles under various conditions in which the molecules can…

Machine Learning · Computer Science 2023-10-11 Jingbang Chen , Yian Wang , Xingwei Qu , Shuangjia Zheng , Yaodong Yang , Hao Dong , Jie Fu

Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce computational complexity, but they typically suffer from a limited…

Computation and Language · Computer Science 2026-02-05 Yunao Zheng , Xiaojie Wang , Lei Ren , Wei Chen

Combining the strengths of many existing predictors to obtain a Mixture of Experts which is superior to its individual components is an effective way to improve the performance without having to develop new architectures or train a model…

Computer Vision and Pattern Recognition · Computer Science 2024-02-02 Kemal Oksuz , Selim Kuzucu , Tom Joy , Puneet K. Dokania

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Huahui Yi , Ziyuan Qin , Wei Xu , Miaotian Guo , Kun Wang , Shaoting Zhang , Kang Li , Qicheng Lao

Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing methods apply uniform negative suppression across all queries, ignoring that the most damaging…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Sriram Mandalika

The success of large pre-trained object detectors hinges on their adaptability to diverse downstream tasks. While fine-tuning is the standard adaptation method, specializing these models for challenging fine-grained domains necessitates…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Vishal Gandhi , Sagar Gandhi

Unsupervised Domain Adaptation (UDA) for object detection aims to adapt a model trained on a source domain to detect instances from a new target domain for which annotations are not available. Different from traditional approaches, we…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Giulio Mattolin , Luca Zanella , Elisa Ricci , Yiming Wang

Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Yang Yang , Wen Wang , Liang Peng , Chaotian Song , Yao Chen , Hengjia Li , Xiaolong Yang , Qinglin Lu , Deng Cai , Boxi Wu , Wei Liu

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, early-fusion language models. MoMa processes images and text in arbitrary sequences by dividing expert modules into…

Artificial Intelligence · Computer Science 2024-08-13 Xi Victoria Lin , Akshat Shrivastava , Liang Luo , Srinivasan Iyer , Mike Lewis , Gargi Ghosh , Luke Zettlemoyer , Armen Aghajanyan

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

Audio-visual learning helps to comprehensively understand the world by fusing practical information from multiple modalities. However, recent studies show that the imbalanced optimization of uni-modal encoders in a joint-learning model is a…

Sound · Computer Science 2023-03-14 Ruize Xu , Ruoxuan Feng , Shi-Xiong Zhang , Di Hu

We consider the problem of Visual Question Answering (VQA). Given an image and a free-form, open-ended, question, expressed in natural language, the goal of VQA system is to provide accurate answer to this question with respect to the…

Computer Vision and Pattern Recognition · Computer Science 2021-06-07 Tanzila Rahman , Shih-Han Chou , Leonid Sigal , Giuseppe Carenini