Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Ming, Yifei"'
Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long context bottlen
Externí odkaz:
http://arxiv.org/abs/2409.17422
Autor:
Nguyen, Xuan-Phi, Pandit, Shrey, Purushwalkam, Senthil, Xu, Austin, Chen, Hailin, Ming, Yifei, Ke, Zixuan, Savarese, Silvio, Xong, Caiming, Joty, Shafiq
Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI. The LLMs used in RAG applica
Externí odkaz:
http://arxiv.org/abs/2409.09916
Autor:
Miyai, Atsuyuki, Yang, Jingkang, Zhang, Jingyang, Ming, Yifei, Lin, Yueqian, Yu, Qing, Irie, Go, Joty, Shafiq, Li, Yixuan, Li, Hai, Liu, Ziwei, Yamasaki, Toshihiko, Aizawa, Kiyoharu
Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other problems are closely related to OOD detection, including anomaly detection
Externí odkaz:
http://arxiv.org/abs/2407.21794
Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning -- a fundamental component of human cognition
Externí odkaz:
http://arxiv.org/abs/2406.14852
Autor:
Ming, Yifei, Li, Yixuan
Pre-trained contrastive vision-language models have demonstrated remarkable performance across a wide range of tasks. However, they often struggle on fine-trained datasets with categories not adequately represented during pre-training, which makes ad
Externí odkaz:
http://arxiv.org/abs/2405.01468
Autor:
Miyai, Atsuyuki, Yang, Jingkang, Zhang, Jingyang, Ming, Yifei, Yu, Qing, Irie, Go, Li, Yixuan, Li, Hai, Liu, Ziwei, Aizawa, Kiyoharu
This paper introduces a novel and significant challenge for Vision Language Models (VLMs), termed Unsolvable Problem Detection (UPD). UPD examines the VLM's ability to withhold answers when faced with unsolvable problems in the context of Visual Ques
Externí odkaz:
http://arxiv.org/abs/2403.20331
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world. However, achieving this can be fundamentally challenging, as it requires the ability to learn invariant features across different domains or
Externí odkaz:
http://arxiv.org/abs/2402.07785
Autor:
Ming, Yifei, Li, Yixuan
Publikováno v:
International Journal of Computer Vision 2023
Recent large vision-language models such as CLIP have shown remarkable out-of-distribution (OOD) detection and generalization performance. However, their zero-shot in-distribution (ID) accuracy is often limited for downstream datasets. Recent CLIP-ba
Externí odkaz:
http://arxiv.org/abs/2306.06048
The ability to generalize to unseen domains is crucial for machine learning systems deployed in the real world, especially when we only have data from limited training domains. In this paper, we propose a simple and effective regularization method ba
Externí odkaz:
http://arxiv.org/abs/2303.07527
Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world. The vast majority of OOD detection methods are driven by a single modality (e.g., either vision or language), leaving the rich informat
Externí odkaz:
http://arxiv.org/abs/2211.13445