Profiles2020-2026
Byoung-Tak Zhang
Seoul National University
18Papers
16Last author
36Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers18
- Learning Coordinate-based Convolutional Kernels for Continuous SE(3) Equivariant and Efficient Point Cloud AnalysisAuthor 4 of 4CVPR 2026
- Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion ModelsAuthor 4 of 4AAAI 2026
- Confidence-guided Refinement Reasoning for Zero-shot Question AnsweringAuthor 5 of 5EMNLP 2025
- On the Consistency of Video Large Language Models in Temporal ComprehensionAuthor 3 of 4CVPR 2025
- DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced LearningAuthor 6 of 6AAAI 2024 · 4 citations
- Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement LearningAuthor 7 of 7AAAI 2024 · 2 citations
- Neural Collage Transfer: Artistic Reconstruction via Material ManipulationAuthor 5 of 5ICCV 2023 · 2 citations
- Learning Geometry-aware Representations by SketchingAuthor 6 of 6CVPR 2023
- Modal-specific Pseudo Query Generation for Video Corpus Moment RetrievalAuthor 5 of 5EMNLP 2022 · 11 citations
- Robust Imitation via Mirror Descent Inverse Reinforcement LearningAuthor 5 of 5NeurIPS 2022 · 5 citations
- Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question AnsweringAuthor 4 of 4ACL 2022
- Smooth-Swap: A Simple Enhancement for Face-Swapping with SmoothnessAuthor 3 of 3CVPR 2022
- DramaQA: Character-Centered Video Story Understanding with Hierarchical QAAuthor 7 of 7AAAI 2021 · 64 citations
- Goal-Aware Cross-Entropy for Multi-Target Reinforcement LearningAuthor 5 of 6NeurIPS 2021 · 11 citations
- Message Passing Adaptive Resonance Theory for Online Active Semi-supervised LearningAuthor 7 of 7ICML 2021 · 10 citations
- Attend What You Need: Motion-Appearance Synergistic Networks for Video Question AnsweringAuthor 4 of 4ACL 2021
- Devil's Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text ClassificationAuthor 3 of 3EMNLP Findings 2021
- Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video DataAuthor 4 of 4AAAI 2020 · 7 citations
