Publications
Publications
[C]onference, [J]ournal, [P]reprint, [W]orkshop
[C15] EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
Conference on Neural Information Processing Systems (NeurIPS), 2025. 🏅Spotlight
Abhiram Kusumba*, Maitreya Patel*, Kyle Min, Changhoon Kim, Chitta Baral, Yezhou Yang
[ paper | code ]
[C14] Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
Conference on Neural Information Processing Systems (NeurIPS), 2025.
Jihoon Kwon, Kyle Min, Jy-yong Sohn
[ paper | code ]
[W9] Data Scaling Isn't Enough: Towards Improving Compositional Reasoning in Video-Language Models
Conference on Neural Information Processing Systems Workshop on EffitientReasoning (NeurIPSW), 2025.
Kibum Kim, Kyle Min, Chanyoung Park
[ paper | code ]
[C13] ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
IEEE International Conference on Computer Vision (ICCV), 2025. 🏅Highlight
Jongseo Lee*, Kyungho Bae*, Kyle Min, Gyeong-Moon Park, Jinwoo Choi (*: equal contribution)
[ paper | code | project page ]
[W8] Edit2Motion: Towards Training-Free Interactive Object-Level Motion Guidance for Image-to-Video Generation
IEEE International Conference on Computer Vision Workshop on HiGen (ICCVW), 2025.
Sainan Liu, Hector A Valdez, Tz-Ying Wu, Sameer Sheorey, Kyle Min, Diana Wofk, Benjamin Ummenhofer, Michael Paulitsch, Subarna Tripathi
[ paper | code ]
[W7] Reinforcement Learning meets Masked Video Modeling: Trajectory-Guided Adaptive Token Selection
IEEE International Conference on Computer Vision Workshop on LongVidFoundations (ICCVW), 2025.
Ayush Rai*, Kyle Min*, Tarun Krishna, Feiyan Hu, Alan F. Smeaton, Noel O'Connor (*: equal contribution)
[ paper | code ]
[W6] EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
IEEE International Conference on Computer Vision Workshop on SAUAFG (ICCVW), 2025.
Ivan Rodin, Tz-Ying Wu, Kyle Min, Sharath Nittur Sridhar, Antonino Furnari, Subarna Tripathi, Giovanni Maria Farinella
[ paper | code ]
[W5] Keystep Recognition using Graph Neural Networks
IEEE Conference on Computer Vision and Pattern Recognition Workshop on EgoVis (CVPRW), 2025.
Julia Romero, Kyle Min, Subarna Tripathi, Morteza Karimzadeh
[ paper | code ]
[C11] Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation
IEEE Winter Conference on Applications of Computer Vision (WACV), 2025.
Utkarsh Nath, Rajeev Goel, Eun Som Jeon, Changhoon Kim, Kyle Min, Yezhou Yang, Yingzhen Yang, Pavan Turaga
[ paper | code | poster | project page ]
[C10] R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
European Conference on Computer Vision (ECCV), 2024. 🏅Oral Presentation
Changhoon Kim*, Kyle Min*, Yezhou Yang (*: equal contribution)
[ paper | code | poster | presentation ]
[C9] WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Preliminary version was presented at the NeurIPS Workshop on Diffusion Models (NeurIPSW), 2023.
Changhoon Kim*, Kyle Min*, Maitreya Patel, Sheng Cheng, Yezhou Yang (*: equal contribution)
[ paper | code | poster | project page ]
[W4] Contrastive Language Video Time Pre-training
IEEE Conference on Computer Vision and Pattern Recognition Workshop on EgoVis (CVPRW), 2024.
Hengyue Liu, Kyle Min, Hector A Valdez, Subarna Tripathi
[ paper | code ]
[W3] STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization
IEEE Conference on Computer Vision and Pattern Recognition Workshop on Ego4D (CVPRW), 2023. 🏅Spotlight
Kyle Min
[ tech report | code ]
[C5] Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
European Conference on Computer Vision (ECCV), 2022.
Kyle Min*, Sourya Roy*, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar (*: equal contribution)
[ paper | code | poster | presentation ]
[W2] Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization
European Conference on Computer Vision Workshop on Ego4D (ECCVW), 2022.
Kyle Min
[ tech report | code ]
[W1] Intel Labs at ActivityNet Challenge 2022: SPELL for Long-Term Active Speaker Detection
IEEE Conference on Computer Vision and Pattern Recognition Workshop on Ego4D (CVPRW), 2022.
Kyle Min, Sourya Roy, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar
[ tech report | presentation ]
[C4] Integrating Human Gaze into Attention for Egocentric Activity Recognition
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.
Kyle Min, Jason J. Corso
[ paper | code | presentation ]
[C3] Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization
European Conference on Computer Vision (ECCV), 2020.
Kyle Min, Jason J. Corso
[ paper | code | poster | presentation ]