updated 2 public sources
Vision-Language Modelsmultimodal reasoningmultimodal evaluation

Current frame

Coauthor on multimodal reasoning and vision-language research

Extended note

Public evidence links Sihang Yuan to ByteDance Seed's Seed1.5-VL Technical Report and to a DBLP author page containing 2025 papers such as "StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models" and "MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity." This supports a conservative profile centered on multimodal reasoning, multimodal evaluation, and vision-language research. No verified public homepage, avatar, education history, or independent work chronology was found from higher-trust exact sources within the research budget.