361 citations
- Carnegie Mellon UniversityUS8 papers
- Stanford UniversityUS6 papers
- Apple (Germany)DE4 papers
- Jet Propulsion LaboratoryUS4 papers
- Amazon (United States)US3 papers
- Aalto UniversityFI2 papers
- Apple (Israel)IL2 papers
- Astronomy and SpaceAU2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Duke UniversityUS2 papers
- École PolytechniqueFR2 papers
- École Polytechnique Fédérale de LausanneCH2 papers
70 papers
Understanding Annotator Safety Policy with Interpretability
Alex Oesterling, Donghao Ren, Yannick Assogba +4
Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from m…
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment
Kai Yuan, Anthony Zheng, Jia Hu +9
Query Auto-Completion (QAC) suggests query completions as users type, helping them articulate intent and reach results more efficiently. Existing approaches face fundamental challe…
Mapping the Design Space of User Experience for Computer Use Agents
Ruijia Cheng, Jenny T. Liang, Eldon Schoop +1
Large language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with thes…
Improving User Interface Generation Models from Designer Feedback
Jason Wu, Amanda Swearngin, Arun Krishna Vajjala +3
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…
EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts
Kushin Mukherjee, Donghao Ren, Dominik Moritz +1
Multimodal vision-language models (VLMs) continue to achieve ever-improving scores on chart understanding benchmarks. Yet, we find that this progress does not fully capture the bre…
Primal-Dual iLQR for GPU-Accelerated Learning and Control in Legged Robots
Lorenzo Amatucci, João Sousa-Pinto, Giulio Turrisi +3
This paper introduces a novel Model Predictive Control (MPC) implementation for legged robot locomotion that leverages GPU parallelization. Our approach enables both temporal and s…