Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

Abstract

Scone unifies subject composition and distinction in subject-driven image generation. Its understanding expert acts as a semantic bridge to guide generation, supported by a two-stage training scheme and the SconeEval benchmark.

Xiaochen Ma

Ph.D. Student in Computer Science and Engineering

I build data infrastructure and high-performance distributed systems that turn heterogeneous data into reliable inputs for large-scale LLM training, with a focus on Ray and Apache Spark.