Yao-Hung Hubert Tsai
24 papers · 2015–2025 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
๐ Conference Polyglot (10) ๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ฃ Hot Topic Early Bird ๐ Academic Marathon (10)
๐
Renaissance Researcher
(7)
๐
Conference Polyglot
(10)
๐
Academic Marathon
(10)
๐ค
Dynamic Duo
(18)
๐
Century Club
(24)
๐
Trend Setter
โก
Prolific Year
(9)
๐๏ธ
Keyword Collector
(92)
Conferences
ICLR (7)
CVPR (3)
EMNLP (3)
NIPS (3)
ACL (2)
ICCV (2)
IJCNLP (1)
JMLR (1)
NAACL (1)
UAI (1)
Top co-authors
Keywords
multimodal learning
(5)
attention mechanism
(4)
representation learning
(2)
cross-domain classification
(2)
sentiment analysis
(2)
neural machine translation
(2)
shapley value
(2)
sequence prediction
(2)
positional embedding
(2)
kernel methods
(2)
modality selection
(2)
submodular maximization
(2)
video understanding
(1)
3d vision
(1)
cross-modal learning
(1)
point cloud
(1)
semantic segmentation
(1)
emotion recognition
(1)
mutual information
(1)
image captioning
(1)
Papers
When LRP Diverges from Leave-One-Out in Transformers
EMNLP 2025
KPConvX: Modernizing Kernel Point Convolution with Kernel Attention
CVPR 2024
Efficient Modality Selection in Multimodal Learning
JMLR 2024
Learning Weakly-supervised Contrastive Representations
ICLR 2022
Greedy modality selection via approximate submodular maximization
UAI 2022
Conditional Contrastive Learning with Kernel
ICLR 2022
Paraphrasing Is All You Need for Novel Object Captioning
NIPS 2022
Self-supervised Learning from a Multi-view Perspective
ICLR 2021
Self-supervised Representation Learning with Relative Predictive Coding
ICLR 2021
Neural Methods for Point-wise Dependency Estimation
NIPS 2020
Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis
EMNLP 2020
Capsules with Inverted Dot-Product Attention Routing
ICLR 2020
Learning Neural Networks with Adaptive Regularization
NIPS 2019
Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
ACL 2019
Multimodal Transformer for Unaligned Multimodal Language Sequences
ACL 2019
Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph
CVPR 2019
Transformer Dissection: An Unified Understanding for Transformerโs Attention via the Lens of Kernel
EMNLP 2019
Learning Factorized Multimodal Representations
ICLR 2019
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
ICLR 2019
Transformer Dissection: An Unified Understanding for Transformerโs Attention via the Lens of Kernel
IJCNLP 2019
Strong and Simple Baselines for Multimodal Utterance Embeddings
NAACL 2019
Learning Robust Visual-Semantic Embeddings
ICCV 2017
Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation
CVPR 2016
Unsupervised Domain Adaptation With Imbalanced Cross-Domain Data
ICCV 2015