Tianyi Zhou

Robust Curriculum Learning: from clean label detection to noisy label self-correction

2021 · International Conference on Learning Representations

Neural network training can easily overfit noisy labels resulting in poor generalization performance. Existing methods address this problem by (1) filtering out the noisy data and only using the clean data for training or (2) …

Structured Cooperative Learning with Graphical Model Priors

2023 · arXiv (Cornell University)

We study how to train personalized models for different tasks on decentralized devices with limited local data. We propose "Structured Cooperative Learning (SCooL)", in which a cooperation graph across devices is generated by a graphical …

1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for …

Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA

2024 · arXiv (Cornell University)

Recent advancements of large language models (LLMs) have led to claims of AI surpassing humans in natural language processing (NLP) tasks such as textual understanding and reasoning. This work investigates these assertions by introducing CAIMIRA, …

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

2025 · arXiv (Cornell University)

Unifying image understanding and generation has gained growing attention in recent research on multimodal models. Although design choices for image understanding have been extensively studied, the optimal model architecture and training recipe for a unified …

DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable …

Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion

2021

Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks, but these graphs are usually incomplete, urging auto-completion of them (a.k.a. knowledge graph completion). Prevalent graph embedding approaches, e.g., TransE, learn structured …

Multi-center federated learning: clients clustering for better personalization

2022 · World Wide Web

Abstract Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy …