Yixuan Shen
I am a first year Ph.D. student in the Department of Computer Science Drexel University, advised by Prof. Feng Liu. Before that, I received my B.S. in Computer Science from Rensselaer Polytechnic Institute.
Philadelphia, PA 19104
My research lies in computer vision and multimodal learning. Recent work includes inverse-physics muscle activation for statistical 3D face models (SIGGRAPH Asia 2026), benchmarking the pedagogical reasoning of multimodal LLMs (AIED 2026), biomechanics-grounded vision–language coaching (CVPR 2026), and cost-aware multi-modal person recognition. See the publications page for the full list.
news
| Sep 28, 2026 | Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning has been accepted at the NeurIPS 2026 Main Track as an Oral Presentation (112/30,709 submissions; ≈ 0.36%)!  |
|---|---|
| Sep 04, 2026 | Our paper MyoFLAME: Inverse-Physics Muscle Activation for Statistical 3D Face Models has been accepted to SIGGRAPH Asia 2026! |
| Jun 24, 2026 | Our preprint What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations is now on arXiv! |
| May 25, 2026 | Our preprint Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning is now on arXiv! |
| Apr 08, 2026 | Our paper From 3D Pose to Prose: Biomechanics-Grounded Vision–Language Coaching has been accepted to CVPR 2026! |
| Apr 08, 2026 | Our paper Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos has been accepted to AIED 2026! |
| Feb 27, 2026 | Our preprint IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognition is now on arXiv! |