Jing Zuo

Jing Zuo is a researcher affiliated with SenseNova who works on native visual reasoning and unified multimodal intelligence. Zuo is listed as an author on publications including VBVR-Pro, a scalable and verifiable testbed for native visual reasoning through visual generation, and SenseNova-U1.5, an 8B mixture-of-transformers model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture. Zuo's research at SenseNova also includes a large-scale evaluation of GPT-6-Astra across twelve robotics benchmarks spanning tabletop manipulation, humanoids, mobile platforms, and dexterous hands.