Zheda Mai

47 papers A* 10Misc 1Journal 32Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time.
CoRR
Sooyoung Jeon, Hongjie Tian, Lemeng Wang, Zheda Mai, Vidhi Bakshi, Jiacheng Hou, Ping Zhang, Arpita Chowdhury, Jianyang Gu, Wei-Lun Chao
2026 J jnl
Prompt-based Adaptation in Large-scale Vision Models: A Survey.
Trans. Mach. Learn. Res.
Xi Xiao, Yunbei Zhang, Lin Zhao, Yiyang Liu, Xiaoying Liao, Zheda Mai, Xingjian Li, Xiao Wang, Hao Xu, Jihun Hamm, Xue Lin, Min Xu, Qifan Wang, Tianyang Wang, Cheng Han
2026 J jnl
Revisiting Model Stitching In the Foundation Model Era.
CoRR
Zheda Mai, Ke Zhang, Fu-En Wang, Zixiao Ken Wang, Albert Y. C. Chen, Lu Xia, Min Sun, Wei-Lun Chao, Cheng-Hao Kuo
2025 J jnl
AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models.
CoRR
Zheda Mai, Arpita Chowdhury, Zihe Wang, Sooyoung Jeon, Lemeng Wang, Jiacheng Hou, Jihyung Kil, Wei-Lun Chao
2025 Misc conf
Attention-Driven Causal Discovery: From Transformer Matrices to Granger Causal Graphs for Non-Stationary Time-series Data.
ICASSP
Jiageng Zhu, Kehao Li, Zheda Mai, Hanchen Xie, Wael AbdAlmageed, Zubin Abraham
2025 J jnl
BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning.
CoRR
Jianyang Gu, Samuel Stevens, Elizabeth G. Campolongo, Matthew J. Thompson, Net Zhang, Jiaman Wu, Andrei Kopanev, Zheda Mai, Alexander E. White, James P. Balhoff, Wasila M. Dahdul, Daniel I. Rubenstein, Hilmar Lapp, Tanya Y. Berger-Wolf, Wei-Lun Chao, Yu Su
2025 J jnl
Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective.
CoRR
Justin Lee, Zheda Mai, Jinsu Yoo, Chongyu Fan, Cheng Zhang, Wei-Lun Chao
2025 — conf
Efficiently Mitigating Video Content Misalignment on Large Vision Model with Time-Series Data Alignment.
CVPR Workshops
Hanchen Xie, Rose Ma, Jiageng Zhu, Zheda Mai, Wael Abd-Almageed, Zubin Abraham
2025 A* conf
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation.
CVPR
Ziheng Zhang, Jianyang Gu, Arpita Chowdhury, Zheda Mai, David Carlyn, Tanya Y. Berger-Wolf, Yu Su, Wei-Lun Chao
2025 J jnl
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation.
CoRR
Ziheng Zhang, Jianyang Gu, Arpita Chowdhury, Zheda Mai, David Carlyn, Tanya Y. Berger-Wolf, Yu Su, Wei-Lun Chao
2025 J jnl
IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation.
CoRR
Yifan Li, Lichi Li, Anh Dao, Xinyu Zhou, Yicheng Qiao, Zheda Mai, Daeun Lee, Zichen Chen, Zhen Tan, Mohit Bansal, Yu Kong
2025 A* conf
Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition.
CVPR
Zheda Mai, Ping Zhang, Cheng-Hao Tu, Hong-You Chen, Quang-Huy Nguyen, Li Zhang, Wei-Lun Chao
2025 — conf
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference.
NAACL (Long Papers)
Zhongwei Wan, Hui Shen, Xin Wang, Che Liu, Zheda Mai, Mi Zhang
2025 J jnl
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference.
CoRR
Zhongwei Wan, Hui Shen, Xin Wang, Che Liu, Zheda Mai, Mi Zhang
2025 J jnl
MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis.
CoRR
Qinghua Liu, Sam Heshmati, Zheda Mai, Zubin Abraham, John Paparrizos, Liu Ren
2025 J jnl
Prompt-CAM: A Simpler Interpretable Transformer for Fine-Grained Analysis.
CoRR
Arpita Chowdhury, Dipanjyoti Paul, Zheda Mai, Jianyang Gu, Ziheng Zhang, Kazi Sajeed Mehrab, Elizabeth G. Campolongo, Daniel I. Rubenstein, Charles V. Stewart, Anuj Karpatne, Tanya Y. Berger-Wolf, Yu Su, Wei-Lun Chao
2025 A* conf
Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis.
CVPR
Arpita Chowdhury, Dipanjyoti Paul, Zheda Mai, Jianyang Gu, Ziheng Zhang, Kazi Sajeed Mehrab, Elizabeth G. Campolongo, Daniel I. Rubenstein, Charles V. Stewart, Anuj Karpatne, Tanya Y. Berger-Wolf, Yu Su, Wei-Lun Chao
2025 J jnl
Prompt-based Adaptation in Large-scale Vision Models: A Survey.
CoRR
Xi Xiao, Yunbei Zhang, Lin Zhao, Yiyang Liu, Xiaoying Liao, Zheda Mai, Xingjian Li, Xiao Wang, Hao Xu, Jihun Hamm, Xue Lin, Min Xu, Qifan Wang, Tianyang Wang, Cheng Han
2025 J jnl
Revisiting semi-supervised learning in the era of foundation models.
CoRR
Ping Zhang, Zheda Mai, Quang-Huy Nguyen, Wei-Lun Chao
2024 J jnl
CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs.
CoRR
Jihyung Kil, Zheda Mai, Justin Lee, Zihe Wang, Kerrie Cheng, Lemeng Wang, Ye Liu, Arpita Chowdhury, Wei-Lun Chao
2024 A* conf
Fine-Tuning is Fine, if Calibrated.
NeurIPS
Zheda Mai, Arpita Chowdhury, Ping Zhang, Cheng-Hao Tu, Hong-You Chen, Vardaan Pahuja, Tanya Y. Berger-Wolf, Song Gao, Charles V. Stewart, Yu Su, Wei-Lun Chao
2024 J jnl
Fine-Tuning is Fine, if Calibrated.
CoRR
Zheda Mai, Arpita Chowdhury, Ping Zhang, Cheng-Hao Tu, Hong-You Chen, Vardaan Pahuja, Tanya Y. Berger-Wolf, Song Gao, Charles V. Stewart, Yu Su, Wei-Lun Chao
2024 J jnl
Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Transfer Learning (PETL) in Visual Recognition.
CoRR
Zheda Mai, Ping Zhang, Cheng-Hao Tu, Hong-You Chen, Li Zhang, Wei-Lun Chao
2024 A* conf
MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs.
NeurIPS
Jihyung Kil, Zheda Mai, Justin Lee, Arpita Chowdhury, Zihe Wang, Kerrie Cheng, Lemeng Wang, Ye Liu, Wei-Lun Chao
2023 A* conf
Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data.
NeurIPS
Cheng-Hao Tu, Hong-You Chen, Zheda Mai, Jike Zhong, Vardaan Pahuja, Tanya Y. Berger-Wolf, Song Gao, Charles V. Stewart, Yu Su, Wei-Lun Chao
2023 J jnl
Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data.
CoRR
Cheng-Hao Tu, Hong-You Chen, Zheda Mai, Jike Zhong, Vardaan Pahuja, Tanya Y. Berger-Wolf, Song Gao, Charles V. Stewart, Yu Su, Wei-Lun Chao
2023 J jnl
Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation.
CoRR
Tianle Chen, Zheda Mai, Ruiwen Li, Wei-Lun Chao
2023 J jnl
Towards understanding and mitigating unintended biases in language model-driven conversational recommendation.
Inf. Process. Manag.
Tianshu Shen, Jiaru Li, Mohamed Reda Bouadjenek, Zheda Mai, Scott Sanner
2023 J jnl
TransCAM: Transformer attention-based CAM refinement for Weakly supervised semantic segmentation.
J. Vis. Commun. Image Represent.
Ruiwen Li, Zheda Mai, Zhibo Zhang, Jongseong Jang, Scott Sanner
2023 A* conf
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning.
CVPR
Cheng-Hao Tu, Zheda Mai, Wei-Lun Chao
2022 J jnl
CVPR 2020 continual learning in computer vision competition: Approaches, results, current challenges and future directions.
Artif. Intell.
Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodríguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vázquez, German Ignacio Parisi, Nikhil Churamani, Marc Pickett, Issam H. Laradji, Davide Maltoni
2022 A* conf
Distributional Contrastive Embedding for Clarification-based Conversational Critiquing.
WWW
Tianshu Shen, Zheda Mai, Ga Wu, Scott Sanner
2022 A* conf
Mitigating the Filter Bubble While Maintaining Relevance: Targeted Diversification with VAE-based Recommender Systems.
SIGIR
Zhaolin Gao, Tianshu Shen, Zheda Mai, Mohamed Reda Bouadjenek, Isaac Waller, Ashton Anderson, Ron Bodkin, Scott Sanner
2022 J jnl
Online continual learning in image classification: An empirical survey.
Neurocomputing
Zheda Mai, Ruiwen Li, Jihwan Jeong, David Quispe, Hyunwoo Kim, Scott Sanner
2022 J jnl
TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation.
CoRR
Ruiwen Li, Zheda Mai, Chiheb Trabelsi, Zhibo Zhang, Jongseong Jang, Scott Sanner
2022 J jnl
Unintended Bias in Language Model-driven Conversational Recommendation.
CoRR
Tianshu Shen, Jiaru Li, Mohamed Reda Bouadjenek, Zheda Mai, Scott Sanner
2022 J jnl
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning.
CoRR
Cheng-Hao Tu, Zheda Mai, Wei-Lun Chao
2021 A* conf
Online Class-Incremental Continual Learning with Adversarial Shapley Value.
AAAI
Dongsub Shim, Zheda Mai, Jihwan Jeong, Scott Sanner, Hyunwoo Kim, Jongseong Jang
2021 J jnl
Online Continual Learning in Image Classification: An Empirical Survey.
CoRR
Zheda Mai, Ruiwen Li, Jihwan Jeong, David Quispe, Hyunwoo Kim, Scott Sanner
2021 — conf
Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning.
CVPR Workshops
Zheda Mai, Ruiwen Li, Hyunwoo Kim, Scott Sanner
2021 J jnl
Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning.
CoRR
Zheda Mai, Ruiwen Li, Hyunwoo Kim, Scott Sanner
2020 J jnl
Adversarial Shapley Value Experience Replay for Task-Free Continual Learning.
CoRR
Zheda Mai, Dongsub Shim, Jihwan Jeong, Scott Sanner, Hyunwoo Kim, Jongseong Jang
2020 — conf
Attentive Autoencoders for Multifaceted Preference Learning in One-class Collaborative Filtering.
ICDM (Workshops)
Zheda Mai, Ga Wu, Kai Luo, Scott Sanner
2020 J jnl
Attentive Autoencoders for Multifaceted Preference Learning in One-class Collaborative Filtering.
CoRR
Zheda Mai, Ga Wu, Kai Luo, Scott Sanner
2020 J jnl
Batch-level Experience Replay with Review for Continual Learning.
CoRR
Zheda Mai, Hyunwoo Kim, Jihwan Jeong, Scott Sanner
2020 J jnl
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions.
CoRR
Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodríguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vázquez, German Ignacio Parisi, Nikhil Churamani, Marc Pickett, Issam H. Laradji, Davide Maltoni
2020 J jnl
Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative Filtering.
CoRR
Jin Peng Zhou, Ga Wu, Zheda Mai, Scott Sanner