Shanghang Zhang

Cross-Domain Sentiment Classification with In-Domain Contrastive Learning

2020 · arXiv (Cornell University)

Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain invariant optimal classifiers rather than …

Triplet Attention

2021

The Transformer model has benefited various real-world applications, where the self-attention mechanism with dot-products shows superior alignment ability on building long dependency. However, the pair-wisely attended self-attention limits further performance improvement on challenging tasks. To …

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency

2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation remains a critical challenge for cross-domain deployment. In addition, existing 3D domain adaptive detection …

Can World Models Benefit VLMs for World Dynamics?

2025 · arXiv (Cornell University)

Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question: with the advent …