6 papers
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
Xiaomin Li, Yuexing Hao, Jianheng Hou +90
Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and inter…
Self-Improving Language Models with Bidirectional Evolutionary Search
Guowei Xu, Zhenting Qi, Huangyuan Su +4
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely…
Intent-aligned Formal Specification Synthesis via Traceable Refinement
Zhe Ye, Aidan Z. H. Yang, Huangyuan Su +6
Large language models are increasingly used to generate code from natural language, but ensuring correctness remains challenging. Formal verification offers a principled way to obt…
Interpreting the linear structure of vision-language model embedding spaces
Isabel Papadimitriou, Huangyuan Su, Thomas Fel +2
Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this jo…
Characterization and Mitigation of Training Instabilities in Microscaling Formats
Huangyuan Su, Mujin Kwun, Stephanie Gil +2
Training large language models is an expensive, compute-bound process that must be repeated as models scale, algorithms improve, and new data is collected. To address this, next-ge…
Data-Efficient Multi-Agent Spatial Planning with LLMs
Huangyuan Su, Aaron Walsman, Daniel Garces +2
In this project, our goal is to determine how to leverage the world-knowledge of pretrained large language models for efficient and robust learning in multiagent decision making. W…