5 papers
EvoMaestro: Toward Interpretable and Steerable LLM-Driven Program Evolution
Feng Liang, Sizhe Cheng, Yikai Li +3
Recent program evolution systems use large language models (LLMs) to generate and iteratively improve populations of programs, producing striking advances in mathematics, algorithm…
ManiScope: LLM-Assisted Visual Analytics of Cryptocurrency Manipulation Risk
Xiaolin Wen, Feng Liang, Yuanye Ma +5
Cryptocurrency markets are vulnerable to trade-based manipulation, such as wash trading, which can distort price signals and mislead investors. Prior research has mainly focused on…
Proteus: Shapeshifting Desktop Visualizations for Mobile via Multi-level Intelligent Adaptation
Can Liu, Sizhe Cheng, Feng Liang +4
With the rise of mobile-first consumption, users increasingly engage with data visualizations on mobile devices. However, the vast majority of existing visualizations are originall…
Probing the Future of Meta-Analysis: Eliciting Design Principles via an Agentic Research IDE
Sizhe Cheng, Feng Liang, Yuhan Wen +2
Meta-analyses and systematic reviews demand rigorous abductive reasoning to build, test, and refine hypotheses across vast, heterogeneous literature. While NLP advancements have au…
PixelArena: A benchmark for Pixel-Precision Visual Intelligence
Feng Liang, Sizhe Cheng, Chenqi Yi +1
Omni-modal models that have multimodal input and output are emerging. However, benchmarking their multimodal generation, especially in image generation, is challenging due to the s…