← Search

Florinel-Alin Croitoru

2 accepted papers

2025

Curriculum Direct Preference Optimization for Diffusion and Consistency Models

CVPR 2025poster

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum learning for text-to-image generation. Our method is divided into t…

2024

Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors

CVPR 2024poster

We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. The novelty of the proposed model is threefold. First we introduce an approach to weight tokens based on motion gradients thus shifting the focus from the static b…