Publications (30)
AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library
Minwei Kong, Ao Qu, Xiaotong Guo +12
Optimization modeling underlies critical decision-making across industries, yet remains difficult to automate: natural-language problem descriptions must be translated into precise…
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
Yihong Tang, Haicheng Liao, Tong Nie +7
End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to co…
ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI
Ao Qu, Yuxi Wen, Jiayi Zhang +6
Classroom observation -- one of the most effective methods for teacher development -- remains limited due to high costs and a shortage of expert coaches. We present ClassMind, an A…
From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models
Yihong Tang, Ao Qu, Xujing Yu +4
Urban and transportation research has long sought to uncover statistically meaningful relationships between key variables and societal outcomes such as road safety, to generate act…
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
Kaichen Zhou, Yuzhen Chen, Fangneng Zhan +8
Video world models can generate realistic futures from a single instruction, but they often fail to track the same physical points consistently across time. As a result, the genera…
Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
Yihong Tang, Ao Qu, Andy H. F. Chow +3
Accurate real-time traffic forecast is critical for intelligent transportation systems (ITS) and it serves as the cornerstone of various smart mobility applications. Though this re…
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
Yihong Tang, Ao Qu, Zhaokai Wang +7
Vision language models (VLMs) perform well on many tasks but often fail at spatial reasoning, which is essential for navigation and interaction with physical environments. Many spa…
MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation
Junlin He, Yihong Tang, Tong Nie +6
Human mobility generation aims to synthesize realistic trip chains for target populations based on individual features. Existing paradigms, including deep generative models, LLM-ba…
HugAgent: Benchmarking LLMs for Simulation of Individualized Human Reasoning
Chance Jiajie Li, Zhenze Mo, Yuhan Tang +11
Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now approximate human responses at scale,…
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Ao Qu, Han Zheng, Zijian Zhou +14
Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods s…
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
Zhenting Qi, Huangyuan Su, Ao Qu +13
How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of d…
Reimagining Urban Science: Scaling Causal Inference with Large Language Models
Yutong Xia, Ao Qu, Yunhan Zheng +8
Urban causal research is essential for understanding the complex, dynamic processes that shape cities and for informing evidence-based policies. However, current practices are ofte…
DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
Yuxuan Gao, Megan Wang, Yi Ling Yu +2
We introduce DecisionBench, a benchmark substrate for emergent delegation in long-horizon agentic workflows. The substrate fixes a task suite (GAIA, tau-bench, BFCL multi-turn), a…
Attacking Deep Reinforcement Learning-Based Traffic Signal Control Systems with Colluding Vehicles
Ao Qu, Yihong Tang, Wei Ma
The rapid advancements of Internet of Things (IoT) and artificial intelligence (AI) have catalyzed the development of adaptive traffic signal control systems (ATCS) for smart citie…
Streaming data preprocessing via online tensor recovery for large environmental sensor networks
Yue Hu, Ao Qu, Yanbing Wang +1
Measuring the built and natural environment at a fine-grained scale is now possible with low-cost urban environmental sensor networks. However, fine-grained city-scale data analysi…
Graph Convolutional Networks for traffic anomaly
Yue Hu, Ao Qu, Dan Work
Event detection has been an important task in transportation, whose task is to detect points in time when large events disrupts a large portion of the urban traffic network. Travel…
What is a typical signalized intersection in a city? A pipeline for intersection data imputation from OpenStreetMap
Ao Qu, Anirudh Valiveru, Catherine Tang +3
Signalized intersections, arguably the most complicated type of traffic scenario, are essential to urban mobility systems. With recent advancements in intelligent transportation te…
Simulating Society Requires Simulating Thought
Chance Jiajie Li, Jiayi Wu, Zhenze Mo +10
Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior; it demands cognitively grounded reasoning that is structured, revi…
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
Keane Ong, Sabri Boughorbel, Luwei Xiao +9
Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts. However, behavioral data is inherently heterogeneous, compr…
FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
Minwei Kong, Chonghe Jiang, Ao Qu +24
Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a…
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
Zijian Zhou, Ao Qu, Zhaoxuan Wu +6
Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries.…
Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at Scale
Vindula Jayawardana, Baptiste Freydt, Ao Qu +6
The sheer scale and diversity of transportation make it a formidable sector to decarbonize. Here, we consider an emerging opportunity to reduce carbon emissions: the growing adopti…
The Last Human-Written Paper: Agent-Native Research Artifacts
Jiachen Liu, Jiaxin Pei, Jintao Huang +34
Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation im…
A Graph Approach to Simulate Twitter Activities with Hawkes Processes
Ao Qu, Ismael Lemhadri
The rapid growth of social media has been witnessed during recent years as a result of the prevalence of the internet. This trend brings an increasing interest in simulating social…
Dissolving the Segmentation of a Shared Mobility Market: A Framework and Four Market Structure Designs
Xiaotong Guo, Ao Qu, Hongmou Zhang +2
In the governance of the shared mobility market of a city or of a metropolitan area, there are two conflicting principles: 1) the healthy competition between multiple platforms, su…
Ozone: A Unified Platform for Transportation Research
Ou Zheng, Ruyi Feng, Yufeng Yang +11
Intelligent Transportation Systems increasingly depend on heterogeneous data from roadside cameras, UAV imagery, LiDAR, and in-vehicle sensors, yet the lack of unified data standar…
IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
Vindula Jayawardana, Baptiste Freydt, Ao Qu +3
Despite the popularity of multi-agent reinforcement learning (RL) in simulated and two-player applications, its success in messy real-world applications has been limited. A key cha…
Less is MoE: Trimming Experts in Domain-Specialist Language Models
Haoze He, Xinkai Zou, Xuan Jiang +4
Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment challenges. Prior MoE compression a…
ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
Yihong Tang, Zhaokai Wang, Ao Qu +11
Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this p…
SEIP: Simulation-based Design and Evaluation of Infrastructure-based Collective Perception
Ao Qu, Xuhuan Huang, Dajiang Suo
Recent advances in sensing and communication have paved the way for collective perception in traffic management, with real-time data sharing among multiple entities. While vehicle-…