85 citations · 92 across the 29 of their papers we have counts for
34 papers
MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation
Mehdi Jafari, Hao Xue, Flora Salim
Steering large language models typically relies on linear, context-independent interventions in activation space, an assumption that recent work has challenged and that can induce…
An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark
Peibo Li, Yang Song, Hao Xue +2
Cross-city point-of-interest (POI) recommendation is crucial for navigating unfamiliar urban environments, yet its progress has historically been constrained by data limitations. U…
Evaluating LLM Personalization via Semantic Constraint Verification
Xuran Li, Guanqin Zhang, Imran Razzak +4
Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols,…
Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling
Ghadir Alselwi, Basem Suleiman, Hao Xue +4
Long-context language modeling requires not only extending context windows but maintaining coherent understanding of entity states and relationships across thousands of tokens -- a…
An Infectious Disease Spread Simulation Based on Large Language Model Decision Making
Yonchanok Khaokaew, Ruochen Kong, Andreas Zufle +6
Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prio…
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
Ruiyi Yang, Zechen Li, Hao Xue +2
Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iterati…
TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation
Wilson Wongso, Lihuan Li, Arian Prabowo +4
Generating high-fidelity synthetic GPS trajectories is increasingly important for applications in transportation, urban planning, and what-if scenario simulation, especially as pri…
SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation
Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2
In this paper, we present SOCIA-Nabla, an end-to-end, agentic framework that treats simulator construction asinstance optimization over code within a textual computation graph. Spe…
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
Ruiyi Yang, Hao Xue, Imran Razzak +2
Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper…
TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis
Feng Tian, Flora D. Salim, Hao Xue
Recent advancements in large language models (LLMs) have enabled powerful agent-based applications in finance, particularly for sentiment analysis, financial report comprehension,…
CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning
Justin Luong, Hao Xue, Flora D. Salim
Physicians routinely assess respiratory sounds during the diagnostic process, providing insight into the condition of a patient's airways. In recent years, AI-based diagnostic syst…
ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents
Zechen Li, Baiyu Chen, Hao Xue +1
Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and typically require costly parameter…
Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
Yue Tan, Xiaoqian Hu, Hao Xue +2
Frontier vision-language models (VLMs) have made remarkable improvements in video understanding tasks. However, real-world videos typically exist as continuously evolving data stre…
Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling
Declan J. Curran, Sanaa Hobeichi, Hira Saleem +2
Downscaling is essential for generating the high-resolution climate data needed for local planning, but traditional methods remain computationally demanding. Recent years have seen…
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
Ruiyi Yang, Hao Xue, Imran Razzak +3
Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling to large kn…
SOCIA-: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation
Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2
In this paper, we present SOCIA-, an end-to-end, agentic framework that treats simulator construction asinstance optimization over code within a textual computation graph.…
Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins -- Dataset and Benchmarks
Wilson Wongso, Hao Xue, Flora D. Salim
Understanding human mobility through Point-of-Interest (POI) trajectory modeling is increasingly important for applications such as urban planning, personalized services, and gener…
Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in Healthcare
Yonchanok Khaokaew, Flora D. Salim, Andreas Züfle +5
Generative agents have been increasingly used to simulate human behaviour in silico, driven by large language models (LLMs). These simulacra serve as sandboxes for studying human b…
RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars
Yuncheng Hua, Lizhen Qu, Zhuang Li +3
Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant…
Long Context Modeling with Ranked Memory-Augmented Retrieval
Ghadir Alselwi, Hao Xue, Shoaib Jameel +3
Effective long-term memory management is crucial for language models handling extended contexts. We introduce the Enhanced Ranked Memory Augmented Retrieval (ERMAR) framework, whic…
Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge Retrieval
Ruiyi Yang, Hao Xue, Imran Razzak +2
Graph Retrieval-Augmented Generation (GraphRAG) has proven highly effective in enhancing the performance of Large Language Models (LLMs) on tasks that require external knowledge. B…
ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting
Futoon M. Abushaqra, Hao Xue, Yongli Ren +1
Addressing the challenges of irregularity and concept drift in streaming time series is crucial for real-world predictive modelling. Previous studies in time series continual learn…
GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender Systems
Wilson Wongso, Hao Xue, Flora D. Salim
Traditional Point-of-Interest (POI) recommendation systems often lack transparency, interpretability, and scrutability due to their reliance on dense vector-based user embeddings.…
SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
Zechen Li, Shohreh Deldari, Linyao Chen +2
We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data. Despite their stro…