ZM
Zheda Mai
cs.CVcs.LGcs.AIcs.IRstat.MLcs.CLcs.DBcs.HCcs.RO
On Valency
published · living versionsW_8yystk3x·v1 · currentpublished
Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
with Jike Zhong, Ming Li, Yuxiang Lai, Xi Xiao +7
1 version
Preprints & journals
25 papers in the corpus · 2020–2026Mind the Tail: Data Selection Through Sparse Concepts2610.21007v1 · Ziheng Zhang, Neha Hulkund, Colin Lee et al.2026 · 0 citationsarXiv
A Study of Failure Modes in Two-Stage Human-Object Interaction Detection2604.13448v1 · Lemeng Wang, Qinqian Lei, Vidhi Bakshi et al.2026 · 0 citationsarXiv
Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time2603.20509v2 · Sooyoung Jeon, Hongjie Tian, Lemeng Wang et al.2026 · 0 citationsarXiv
Revisiting Model Stitching In the Foundation Model Era2603.12433v3 · Zheda Mai, Ke Zhang, Fu-En Wang et al.2026 · 0 citationsarXiv
IndustryNav: Evaluating Spatial Reasoning and Safety of Embodied Agents in Dynamic Industrial Navigation2511.17384v3 · Yifan Li, Lichi Li, Anh Dao et al.2025 · 0 citationsarXiv
Prompt-based Adaptation in Large-scale Vision Models: A Survey2510.13219v2 · Xi Xiao, Yunbei Zhang, Lin Zhao et al.2025 · 1 citationarXiv
MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis2510.07513v1 · Qinghua Liu, Sam Heshmati, Zheda Mai et al.2025 · 0 citationsarXiv
BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning2505.23883v2 · Jianyang Gu, Samuel Stevens, Elizabeth G Campolongo et al.2025 · 8 citationsarXiv
Revisiting semi-supervised learning in the era of foundation models2503.09707v4 · Ping Zhang, Zheda Mai, Quang-Huy Nguyen et al.2025 · 1 citationarXiv
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation2501.11309v2 · Ziheng Zhang, Jianyang Gu, Arpita Chowdhury et al.2025 · 19 citationsarXiv
Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis2501.09333v2 · Arpita Chowdhury, Dipanjyoti Paul, Zheda Mai et al.2025 · 8 citationsarXiv
Fine-Tuning is Fine, if Calibrated2409.16223v3 · Zheda Mai, Arpita Chowdhury, Ping Zhang et al.2024 · 6 citationsarXiv
Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition2409.16434v5 · Zheda Mai, Ping Zhang, Cheng-Hao Tu et al.2024 · 12 citationsarXiv
Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data2311.01420v1 · Cheng-Hao Tu, Hong-You Chen, Zheda Mai et al.2023 · 2 citationsarXiv
Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation2305.05803v4 · Tianle Chen, Zheda Mai, Ruiwen Li et al.2023 · 40 citationsarXiv
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning2212.03220v2 · Cheng-Hao Tu, Zheda Mai, Wei-Lun Chao2022 · 44 citationsarXiv
TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation2203.07239v1 · Ruiwen Li, Zheda Mai, Chiheb Trabelsi et al.2022 · 96 citationsJournal of Visual Communication and Image Representation 2023
Unintended Bias in Language Model-driven Conversational Recommendation2201.06224v2 · Tianshu Shen, Jiaru Li, Mohamed Reda Bouadjenek et al.2022 · 3 citationsarXiv
Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning2103.13885v3 · Zheda Mai, Ruiwen Li, Hyunwoo Kim et al.2021 · 190 citationsarXiv
Online Continual Learning in Image Classification: An Empirical Survey2101.10423v4 · Zheda Mai, Ruiwen Li, Jihwan Jeong et al.2021 · 416 citationsarXiv
Attentive Autoencoders for Multifaceted Preference Learning in One-class Collaborative Filtering2010.12803v1 · Zheda Mai, Ga Wu, Kai Luo et al.2020 · 2 citationsarXiv
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions2009.09929v1 · Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez et al.2020 · 49 citationsarXiv
Online Class-Incremental Continual Learning with Adversarial Shapley Value2009.00093v4 · Dongsub Shim, Zheda Mai, Jihwan Jeong et al.2020 · 197 citationsarXiv
Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative Filtering2008.01246v2 · Jin Peng Zhou, Ga Wu, Zheda Mai et al.2020 · 2 citationsarXiv
Batch-level Experience Replay with Review for Continual Learning2007.05683v1 · Zheda Mai, Hyunwoo Kim, Jihwan Jeong et al.2020 · 14 citationsarXiv
Career total: 41 works. 25 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.