Qi Tian

A Semi-Supervised Assessor of Neural Architectures

2020 · arXiv (Cornell University)

Neural architecture search (NAS) aims to automatically design deep neural networks of satisfactory performance. Wherein, architecture performance predictor is critical to efficiently value an intermediate neural architecture. But for the training of this predictor, a …

Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations

2020 · arXiv (Cornell University)

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents heterogeneous contrastive learning (HCL), an effective approach …

Global or Local: Constructing Personalized Click Models for Web Search

2022 · Proceedings of the ACM Web Conference 2022

Click models are widely used for user simulation, relevance inference, and evaluation in Web search. Most existing click models implicitly assume that users’ relevance judgment and behavior patterns are homogeneous. However, previous studies have shown …

Domain-Agnostic Prior for Transfer Semantic Segmentation

2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. The key difficulty lies in defining a common property between the source and target domains so that the source-domain features can align …

Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering

2023 · arXiv (Cornell University)

Explainable question answering (XQA) aims to answer a given question and provide an explanation why the answer is selected. Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured …

Exploring Effective Mask Sampling Modeling for Neural Image Compression

2023 · arXiv (Cornell University)

Image compression aims to reduce the information redundancy in images. Most existing neural image compression methods rely on side information from hyperprior or context models to eliminate spatial redundancy, but rarely address the channel redundancy. …

Federated Domain Generalization with Generalization Adjustment

2023

Federated Domain Generalization (FedDG) attempts to learn a global model in a privacy-preserving manner that generalizes well to new clients possibly with domain shift. Recent exploration mainly focuses on designing an unbiased training strategy within …

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

2023 · arXiv (Cornell University)

Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden largely restricts the application of LLMs especially when one needs to …

SPARC: Soft Probabilistic Adaptive multi-interest Retrieval Model via Codebooks for recommender system

2025 · arXiv (Cornell University)

Modeling multi-interests has arisen as a core problem in real-world RS. Current multi-interest retrieval methods pose three major challenges: 1) Interests, typically extracted from predefined external knowledge, are invariant. Failed to dynamically evolve with users' …