Publications
46
Citations
316
Est. group size
~2
Recurring co-author estimate
Active years
15
Publishing since 2012
This bibliographic record appears to blend two distinct research strands under one name: earlier work (2016-2019) on medical imaging, including intravascular optical imaging of arterial plaques and biosensor-based bacteria detection, and more recent work (2023-2026) on computer vision and 3D graphics topics such as point-cloud generation, amodal segmentation, vision-language models, and 3D model quantization. Prospective students should verify which body of work matches the specific lab or advisor they are considering, since these two areas rarely overlap and may represent different researchers or a career shift. The recent output centers on AI methods for 3D reconstruction, segmentation, and multimodal (vision+language) model evaluation.
Publication output was low and sporadic from 2017-2022 (0-1 per year) but has grown sharply since 2023, reaching 8 in 2026, indicating a recent increase in activity.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models
Proceedings of the AAAI Conference on Artificial Intelligence · 2026
- Language-guided invariance probing of vision–language models
Pattern Recognition Letters · 2026
- Language-guided invariance probing of vision–language models
Pattern Recognition Letters · 2026
- 3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models
arXiv (Cornell University) · 2026
- 3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models
arXiv (Cornell University) · 2026
- A-Occ-Plant: Plant occluded point cloud completion via amodal segmentation
Plant Phenomics · 2026
- Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks
arXiv (Cornell University) · 2026
- Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks
arXiv (Cornell University) · 2026
- RGB2Point: 3D Point Cloud Generation from Single RGB Images
2025
- Top2Ground: A Height-Aware Dual Conditioning Diffusion Model for Robust Aerial-to-Ground View Generation
arXiv (Cornell University) · 2025
- WebAccessVL: Violation-Aware VLM for Web Accessibility
arXiv (Cornell University) · 2025
- Hands-Free VR
arXiv (Cornell University) · 2024
- RGB2Point: 3D Point Cloud Generation from Single RGB Images
arXiv (Cornell University) · 2024
- Latent L-systems: Transformer-based Tree Generator
ACM Transactions on Graphics · 2023
- SnakeVoxFormer: Transformer-based Single Image\\Voxel Reconstruction with Run Length Encoding
arXiv (Cornell University) · 2023
- arXiv (Cornell University)×11
- Journal of the American College of Cardiology×4
- Pattern Recognition Letters×2
- Journal of Microbiological Methods×1
- Ergonomics×1
- Josephine Pyles
Medicine · Indiana University
- Mikhail Tarasov
Medicine · The Ohio State University
- Ahmed ElGuindy
Medicine · The Ohio State University
- Craig A. Thompson
Medicine · Purdue University West Lafayette
- Dean J. Kereiakes
Medicine · The Ohio State University
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile