CVPR'24 · SynData
GenAI‑Bench
Evaluating and improving compositional text‑to‑visual generation.
★ Best Short Paper
Vision‑language, video understanding, and the human‑in‑the‑loop systems that make modern multimodal models actually useful.
Evaluating and improving compositional text‑to‑visual generation.
Towards understanding camera motions in any video — dataset and benchmarks track.
Building a precise video language with human–AI oversight — the loop powering Moodio.
I move between research, product strategy, AI workflows and high‑fidelity craft — building 0‑to‑1 across B2B and B2C.
Hi :‑D — I'm a full‑stack Product Designer, Program Manager and AI‑startup founder based in Menlo Park. I have 4+ years leading 0‑to‑1 product design, agent workflows, and cross‑functional execution across B2B and B2C.
Strong background in UX/UI, product strategy and user research, with hands‑on expertise in using AI to prototype and execute across design, product and data pipelines. Track record of improving operational efficiency, driving product growth, and contributing to top‑tier academic research.
M.S. from Carnegie Mellon (Integrated Innovation for Products & Services, 2022). BFA from Parsons (Communication Design, 2021, Merit Scholarship).
Open to collaborations on AI products, agent workflows, and 0‑to‑1 design partnerships. Menlo Park · O‑1B · 72‑hour reply.
ttiffanyyllingg@gmail.com