Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models
Benjamin Yu, Jackie Liu, Justin Cui
Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for rein…
cs.CV2025
Latent Video Dataset Distillation
Ning Li, Antai Andy Liu, Jingran Zhang +1
Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existin…
cs.CV2025
Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability
Ning Li, Jingran Zhang, Justin Cui
OpenAI's multimodal GPT-4o has demonstrated remarkable capabilities in image generation and editing, yet its ability to achieve world knowledge-informed semantic synthesis--seamles…