2026-09-22T22:13:12Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/132611 2026-03-24 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

application/pdf en text Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-12-01 The student, Hanlin Mai, accepted the attached license on 2025-12-11 at 10:55. The student, Hanlin Mai, submitted this Thesis for approval on 2025-12-11 at 11:05. This Thesis was approved for publication on 2025-12-11 at 11:45. DSpace SAF Submission Ingestion Package generated from Vireo submission #22744 on 2026-02-19 at 18:45:09 Analysis of errors in generative image and video models Mai, Hanlin 2025-12-11 Lazebnik, Svetlana Generative AI Diffusion Models eng Image and video generative models have become increasingly powerful and produce visuals that are more difficult to distinguish from real ones in recent years. Users can create images and videos to make their imaginations come true easier than ever before. However, on closer examination, these models make interesting mistakes. In this thesis, we first discuss a systematic way of analyzing errors in generated images relating to projective geometry and shadows at a population level. We find that generated images can be reliably distinguished from real images by derived geometric features alone without looking at pixels. Then, we introduce methods that can effectively judge whether a generated video is physically plausible for robotic demonstrations. 2025-12 Thesis https://hdl.handle.net/2142/132611 Copyright 2025 Hanlin Mai Electrical & Computer Eng Electrical & Computer Engr University of Illinois Urbana-Champaign M.S. Thesis