Dimitris Samaras

Full Professor@Stony Brook University·美国·OpenReview

研究方向

Computer Vision · Medical Imaging · fMRI analysis · Machine Learning · Generative Models · Digital Histopathology · Face and Gesture · Illumination Modeling

6.7

Generating metamers of human scene understanding

ICLR 2026Oral

5.3

PISCES: Annotation-free Text-to-Video Post-Training via Bi-objective OT-aligned Rewards

ICLR 2026Desk Rejected

合作者 (20)

Dimitris Samaras

Generating metamers of human scene understanding

PISCES: Annotation-free Text-to-Video Post-Training via Bi-objective OT-aligned Rewards

Mitigating Diffusion Model Hallucinations with Dynamic Guidance

CDG-MAE: Learning Correspondences from Diffusion Generated Views

Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment

Low-Rank Head Avatar Personalization with Registers

TopoDiffusionNet: A Topology-aware Diffusion Model

Fast constrained sampling in pre-trained diffusion models

Fast constrained sampling in pre-trained diffusion models