Research scientist · ByteDance
I build AI systems that learn the dynamics of the world — from extreme weather and generative models to reasoning agents that act in it.
WeatherGenerative modelingAgents & LLMs
Scholar snapshot June 2026
01 / Selected work
Three research threads trace a path from modeling physical dynamics to measuring and building capable agents.
Weather intelligence · Nature 2023
A generative nowcasting system that combines physical-evolution priors with data-driven learning for large-area, short-term extreme precipitation prediction.
Agent evaluation · arXiv 2025
A profession-aligned evaluation suite for measuring real-world productivity scaling and market readiness of AI agents.
Generalized agency · arXiv 2026
A model card for an agent model designed around perception, reasoning, and action across diverse professional domains.
02 / Publications
Ten papers across weather intelligence, generative modeling, multimodal reasoning, scaling, and agents.
Open the filterable archive01
arXiv · Agents · LLMs
02
arXiv · Visual reasoning
03
arXiv · Agent benchmark
04
05
arXiv · Reasoning · RL
06
arXiv · Agents · Scaling
07
arXiv · LLMs · Scaling
08
arXiv · LLMs · Scaling
09
ICML 2024 · Diffusion
10
Nature 2023 · AI for weather
Citation counts are a dated Google Scholar snapshot from June 2026.
03 / Profile
Kaiyuan Chen is a Research Scientist at ByteDance. His work spans forecasting, generative modeling, multimodal reasoning, evaluation, and real-world agents.
Education
2021 — 2024
Machine Learning Lab, School of Software
Tsinghua University
2017 — 2021
Department of Mathematical Sciences
Tsinghua University