James Liang

4 papers · 2022–2025 · 3 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

NeurIPS (2) ECCV (1) ICCV (1)

Top co-authors

Dongfang Liu (4) Qifan Wang (2) Wenguan Wang (2) Tong Geng (1) Zhiyuan Cheng (1) Xiangyu Zhang (1) Yiming Cui (1) Ruixiang Tang (1) Luna Xinyu Zhang (1) Taowen Wang (1)

Research topics

Machine Learning (3) Computer Vision (2) Deep Learning (2) Analysis (2) Architectures (2) Core Methods (2) Learning Types · Machine Learning (2) Artificial Intelligence (1) Core AI (1) Learning Types · Deep Learning (1)

Keywords

instance segmentation (2) robotic manipulation (1) object detection (1) query embedding (1) clustering paradigms (1) adversarial attack (1) geometric transformation (1) cross-attention mechanism (1) equivariant representation (1) security vulnerability (1) adversarial patch (1) query-based model (1) feature dispatching (1) transformation equivariance (1) instance separation (1) image classification (1) instance-aware embedding (1)

Papers

Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics ICCV 2025 ClusterFomer: Clustering As A Universal Visual Learner NeurIPS 2023 Learning Equivariant Segmentation with Instance-Unique Querying NeurIPS 2022 Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches ECCV 2022