Ph.D. thesis: 'Towards a Unified Framework for Visual Recognition and Generation via Masked Generative Modeling' (defended May 2024).
NeurIPS 2024 paper 'Autoregressive Image Generation without Vector Quantization' – Spotlight (top 2%).
NeurIPS 2024 paper 'Return of Unconditional Generation' – Oral (top 0.4%).
ICLR 2024 paper 'Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency' – Spotlight (top 5%).
CVPR 2023 paper 'MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis'.
CVPR 2020 Oral paper 'Learning Longterm Representations for Person Re-Identification Using Radio Signals'.
Published numerous papers at top-tier conferences (NeurIPS, ICLR, CVPR, ECCV, WACV, etc.), many with code, demos, and media coverage (e.g., MIT News, TechCrunch).
Co-organized the CVPR 2025 workshop 'Visual Generative Modeling: What’s After Diffusion?' in June 2025.