Jiajun Wu

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual generative modeling.

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reducing token usage.

The paper addresses the challenge of multi-turn view planning for VLMs by proposing an iterative framework that uses self-exploration and view graph distillation, significantly improving planning performance over state-of-the-art models.

This paper introduces DIRECT, a routing framework that allocates test-time compute per prompt to improve the success--cost Pareto frontier for embodied agents.