Yankai Yang — accepted AI-conference papers

2026

SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning

Yancheng Long, Yankai Yang, Hongyang Wei, Wei Chen, Tianke Zhang, Haonan Fan +9

ICML 2026poster

Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle with a critical perception gap we term "Attention Collapse," where models neglect c…

Cited by 0 Source ↗Scholar ↗

2025

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

Asal Mehradfar, Xuzhe Zhao, Yilun Huang, Emir Ceyani, Yankai Yang, Shihao han +2

NeurIPS 2025poster

Designing analog circuits from performance specifications is a complex, multi-stage process encompassing topology selection, parameter inference, and layout feasibility. We introduce FALCON, a unified machine learning framework that enables fully automated, specification-driven analog circuit synthe…

Cited by 0 Source ↗code ↗Scholar ↗