Yoshinari Fujinuma
Member of Technical Staff, Research
Yoshi is a research scientist at Patronus AI who works on LLM judges, diffusion language models and agent benchmarks such as SpeedrunBench and FigmaTrace. Before Patronus, he was a member of technical staff at Cantina Labs and a senior applied scientist at AWS AI Labs, and he holds a PhD in computer science from the University of Colorado Boulder.
At Patronus
Papers
October 6, 2026
speedrunbench
https://arxiv.org/abs/2610.08076
August 20, 2026
figmatrace
https://arxiv.org/abs/2608.21460
June 1, 2026
skill-injection-attacks
https://arxiv.org/abs/2606.01567
April 4, 2026
Workshop
prompt-infilling-for-diffusion-lms
https://arxiv.org/abs/2604.03677
COLM 2026 Workshop
October 21, 2025
Main
contrastive-decoding-for-llm-judges
https://arxiv.org/abs/2510.18196
Findings of ACL 2026
Posts
We Built Our Own Post-Training Stack to Measure What Our Tasks Are Worth
post-training-stack
Introducing SpeedrunBench: A Challenging Benchmark for Frontier Agents
introducing-speedrunbench-a-challenging-benchmark-for-frontier-agents
Introducing FigmaTrace: A Comprehensive Training Dataset for Figma Design Workflows
figmatrace-a-comprehensive-training-dataset-for-figma-design-workflows
Getting GLM-5.2 NVFP4 Post-Training Off the Ground
getting-glm-5-2-nvfp4-post-training-off-the-ground
No papers or posts here yet.
Work with Yoshinari
See open roles →Yoshinari Fujinuma
show