Tootfinder

Improving User Interface Generation Models from Designer Feedback
Jason Wu, Amanda Swearngin, Arun Krishna Vajjala, Alan Leung, Jeffrey Nichols, Titus Barik
https://arxiv.org/abs/2509.16779

Improving User Interface Generation Models from Designer Feedback
Despite being trained on vast amounts of data, most LLMs are unable to reliably generate well-designed UIs. Designer feedback is essential to improving performance on UI generation; however, we find that existing RLHF methods based on ratings or rankings are not well-aligned with designers' workflows and ignore the rich rationale used to critique and improve UI designs. In this paper, we investigate several approaches for designers to give feedback to UI generation models, using familiar intera…

At least 2/3 of Americans aren’t daily coffee drinkers. ☕️
Wait, they are.
Well, at least hundreds of millions of American coffee drinkers don’t drink an average of 3 cups a day.
Wait, they do.
Folks, these are #TrumpTariffs, taking money from the American people.
via @…

CLF-RL: Control Lyapunov Function Guided Reinforcement Learning
Kejun Li, Zachary Olkin, Yisong Yue, Aaron D. Ames
https://arxiv.org/abs/2508.09354 https://

CLF-RL: Control Lyapunov Function Guided Reinforcement Learning
Reinforcement learning (RL) has shown promise in generating robust locomotion policies for bipedal robots, but often suffers from tedious reward design and sensitivity to poorly shaped objectives. In this work, we propose a structured reward shaping framework that leverages model-based trajectory generation and control Lyapunov functions (CLFs) to guide policy learning. We explore two model-based planners for generating reference trajectories: a reduced-order linear inverted pendulum (LIP) mode…