الباحثون

Fengyu Cai

المنشورات 2

نسخة أولية وصول مفتوح

World Embedding Benchmark

Yiqi Liu, Ruifeng Yuan, Yang Wang وآخرون · 2026

Physical fidelity has received increasing attention in world models and video generation, yet how video representations encode physical information remains less understood. We introduce the World Embedding Benchmark, comprising 8,000 controlled simulation cases from 80 families spanning fluid mechanics, solid mechanics …

نسخة أولية وصول مفتوح

AutoDataBench: A Data-centric Testbed for Accelerating Auto Research

Ruifeng Yuan, Yizhi Li, Yaxin Du وآخرون · 2026

Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and data, making it difficult to attribute why one frontier agent outperforms another to specific research capabilities. In this work, we isolate and systematically evaluate …

المؤلفون المشاركون