2 citations · 5 across the 11 of their papers we have counts for
13 papers
Steering Vectors as a Training Signal in LLM Post-Training
Tiejin Chen, Maunil Vyas, Huaiyuan Yao +1
Steering vectors (SVs) are residual-stream directions that shift the behavior of LLMs when added to hidden states at inference time. While prior work has mainly used SVs as post-ho…
MAVE: A Multi-Agent Framework for Grounded Pedagogical Feedback from Online Class Videos
Qingyue Chen, Huaiyuan Yao, Wanpeng Xu +3
Timely pedagogical feedback is difficult to scale in online classes, where long and noisy videos make student responses hard to locate and automated systems often produce generic a…
Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control
Ferdous Al Rafi, Susrik Mukherjee, Latika Liladhar Dekate +6
Reinforcement learning achieves strong traffic signal control performance in simulation, yet policies trained in simulators often fail once deployed in the real world, a failure kn…
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems
Huaiyuan Yao, Xiaoou Liu, Charles Fleming +2
LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection me…
Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition
Tiejin Chen, Huaiyuan Yao, Jia Chen +2
While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions introduce critical reliabilit…
LangMARL: Natural Language Multi-Agent Reinforcement Learning
Huaiyuan Yao, Longchao Da, Xiaoou Liu +3
Large language model (LLM) agents struggle to autonomously evolve coordination strategies in dynamic environments, largely because coarse global outcomes obscure the causal signals…
From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges
Yihan Hong, Huaiyuan Yao, Bolin Shen +3
Rubric-based text evaluation increasingly relies on large language models (LLMs) as scalable judges, yet frozen black-box models can interpret the same criteria inconsistently, pro…
Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design
Huaiyuan Yao, Wanpeng Xu, Justin Turnau +2
Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and tea…
Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation
Jianjiang Yang, Ziyan Huang, Yanshu li +2
Despite remarkable progress in image quality and prompt fidelity, text-to-image (T2I) diffusion models continue to exhibit persistent "hallucinations", where generated content subt…
FUAS-Agents: Autonomous Multi-Modal LLM Agents for Treatment Planning in Focused Ultrasound Ablation Surgery
Lina Zhao, Zihao Bian, Qingyue Chen +8
Focused Ultrasound Ablation Surgery (FUAS) has emerged as a promising non-invasive therapeutic modality, valued for its safety and precision. Nevertheless, its clinical implementat…
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
Huaiyuan Yao, Pengfei Li, Bu Jin +7
Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability…
Generative AI in Transportation Planning: A Survey
Longchao Da, Tiejin Chen, Zhuoheng Li +14
The integration of generative artificial intelligence (GenAI) into transportation planning has the potential to revolutionize tasks such as demand forecasting, infrastructure desig…
CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic
Huaiyuan Yao, Longchao Da, Vishnu Nandam +4
The integration of autonomous vehicles into urban traffic has great potential to improve efficiency by reducing congestion and optimizing traffic flow systematically. In this paper…