Hongzhi Li

4 papers · 2015–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze

Venues

ACL (1) CVPR (1) EMNLP (1) NAACL (1)

Top co-authors

Tongtao Zhang (2) Heng Ji (2) Shih-fu Chang (2) Mei Si (1) Rostyslav Korolov (1) Jiawei Han (1) Angel X Chang (1) Jie Wu (1) Di Lu (1) Zicheng Liu (1)

Research topics

Artificial Intelligence (1) Computer Vision (1) Deep Learning (1) Machine Learning (1) Natural Language Processing (1) Analysis (1) Architectures (1) Core AI (1) Core Methods (1) Generation (1) Learning Types (1)

Keywords

object detection (1) classification head (1) classification accuracy (1) retrieval-augmented generation (1) spurious feature (1) feature pyramid (1) bounding box regression (1) data synthesis pipeline (1) robustness quantification (1) double head (1) fully connected head (1) convolution head (1)

Papers

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data ACL 2026 Rethinking Classification and Localization for Object Detection CVPR 2020 Cross-media Event Extraction and Recommendation NAACL 2016 Cross-document Event Coreference Resolution based on Cross-media Features EMNLP 2015