Or Patashnik
2 papers · Latest:
Machine Learning
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
ParetoSlider trains a single diffusion model using multi-objective RL to provide continuous, inference-time control over conflicting rewards.
2604.20816
Computer VisionHDR Video Generation via Latent Alignment with Logarithmic Encoding
This paper enables high-quality HDR video generation by aligning logarithmically encoded HDR data with pretrained generative models' latent spaces.
2604.11788
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.