340 citations · 412 across the 16 of their papers we have counts for
16 papers
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
Zirui Wang, Yusen Hou, Shaofeng Liang +4
The explosive growth of large language models (LLMs) has created a heterogeneous and poorly documented ecosystem, making systematic model comparison increasingly important for prov…
TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models
Tingfeng Lan, Zirui Wang, Yunjia Zheng +3
Modern model hubs store hundreds of petabytes of large language models (LLMs), with fine-tuned variants dominating the storage footprint. These variants contain substantial cross-m…
PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
Hefei Mei, Zirui Wang, Chang Xu +2
Large Vision-Language Models (LVLMs) are foundational to modern multimodal applications, yet their susceptibility to adversarial attacks remains a critical concern. Prior white-box…
Guiding Image Captioning Models Toward More Specific Captions
Simon Kornblith, Lala Li, Zirui Wang +1
Image captioning is conventionally formulated as the task of generating captions for images that match the distribution of reference image-caption pairs. However, reference caption…
Generative Data Augmentation for Non-IID Problem in Decentralized Clinical Machine Learning
Zirui Wang, Shaoming Duan, Chengyue Wu +4
Swarm learning (SL) is an emerging promising decentralized machine learning paradigm and has achieved high performance in clinical applications. SL solves the problem of a central…
REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory
Ziniu Hu, Ahmet Iscen, Chen Sun +6
In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it…
VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
Shen Yan, Tao Zhu, Zirui Wang +5
We explore an efficient approach to establish a foundational video-text model. We present VideoCoCa that maximally reuses a pretrained image-text contrastive captioner (CoCa) model…
Exploiting Category Names for Few-Shot Classification with Vision-Language Models
Taihong Xiao, Zirui Wang, Liangliang Cao +3
Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks. Notably, many vision-language models build two encoder…
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Jiahui Yu, Yuanzhong Xu, Jing Yu Koh +14
We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compos…
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
Jinjin Gu, Haoming Cai, Chao Dong +47
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (…
On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
Zirui Wang, Zachary C. Lipton, Yulia Tsvetkov
Modern multilingual models are trained on concatenated text from multiple languages in hopes of conferring benefits to each (positive transfer), with the most pronounced benefits a…
Efficient Meta Lifelong-Learning with Limited Memory
Zirui Wang, Sanket Vaibhav Mehta, Barnabás Póczos +1
Current natural language processing models work well on a single task, yet they often fail to continuously learn new tasks without forgetting previous ones as they are re-trained t…
Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework
Zirui Wang, Jiateng Xie, Ruochen Xu +3
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such represen…
Theoretical Guarantees of Transfer Learning
Zirui Wang
Transfer learning has been proven effective when within-target labeled data is scarce. A lot of works have developed successful algorithms and empirically observed positive transfe…
Characterizing and Avoiding Negative Transfer
Zirui Wang, Zihang Dai, Barnabás Póczos +1
When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task. However, when transferrin…
Towards more Reliable Transfer Learning
Zirui Wang, Jaime Carbonell
Multi-source transfer learning has been proven effective when within-target labeled data is scarce. Previous work focuses primarily on exploiting domain similarities and assumes th…