120 citations · 208 across the 25 of their papers we have counts for
26 papers
FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search
James Xu Zhao, Hui Chen, Bryan Hooi +1
Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to improve thes…
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
Zhiyuan Hu, Yunhai Hu, Juncheng Liu +9
Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL)…
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Zhiyuan Hu, Yucheng Wang, Yufei He +7
Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from explor…
Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
James Xu Zhao, Bryan Hooi, See-Kiong Ng
Test-time scaling increases inference-time computation through longer reasoning chains and has shown strong performance gains across many domains. However, frontier models still su…
SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
Adam Goodge, Xun Xu, Bryan Hooi +4
As point cloud data increases in prevalence in a variety of applications, the ability to detect out-of-distribution (OOD) point cloud objects becomes critical for ensuring model sa…
How Does Response Length Affect Long-Form Factuality
James Xu Zhao, Jimmy Z. J. Liu, Bryan Hooi +1
Large language models (LLMs) are widely used for long-form text generation. However, factual errors in the responses would undermine their reliability. Despite growing attention to…
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Zhiyuan Hu, Yibo Wang, Hanze Dong +5
Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning. Prior work has shown that outcome-based reinforcement learning (RL) can inciden…
Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
Zhiyuan Hu, Shiyun Xiong, Yifan Zhang +5
Recent advancements in visual language models (VLMs) have notably enhanced their capabilities in handling complex Graphical User Interface (GUI) interaction tasks. Despite these im…
Geneshift: Impact of different scenario shift on Jailbreaking LLM
Tianyi Wu, Zhiwei Xue, Yue Liu +3
Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack…
Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
Adam Goodge, Wee Siong Ng, Bryan Hooi +1
Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and lang…
Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning
Tianyi Wu, Jingwei Ni, Bryan Hooi +5
Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to…
CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
Jinlan Fu, Shenzhen Huangfu, Hao Fei +4
Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct…
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Zhiyuan Hu, Yuliang Liu, Jinman Zhao +8
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts t…
When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
Adam Goodge, Bryan Hooi, Wee Siong Ng
Contrastive Language-Image Pre-training (CLIP) achieves remarkable performance in various downstream tasks through the alignment of image and text input embeddings and holds great…
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
Zhiyuan Hu, Chumin Liu, Xidong Feng +6
In the face of uncertainty, the ability to *seek information* is of fundamental importance. In many practical applications, such as medical diagnosis and troubleshooting, the infor…
Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals
Zhiyuan Hu, Yue Feng, Yang Deng +4
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular…
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Miao Xiong, Zhiyuan Hu, Xinyang Lu +4
Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which prim…
Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System
Zhiyuan Hu, Yue Feng, Anh Tuan Luu +2
Dialogue systems and large language models (LLMs) have gained considerable attention. However, the direct utilization of LLMs as task-oriented dialogue (TOD) models has been found…
PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation
Zhiyuan Hu, Chumin Liu, Yue Feng +2
Controllable text generation is a challenging and meaningful field in natural language generation (NLG). Especially, poetry generation is a typical one with well-defined and strict…
TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks
Baixiang Huang, Bryan Hooi, Kai Shu
Road safety is a major global public health concern. Effective traffic crash prediction can play a critical role in reducing road traffic accidents. However, Existing machine learn…
Joint Triplet Loss Learning for Next New POI Recommendation
Nicholas Lim, Bryan Hooi, See-Kiong Ng +1
Sparsity of the User-POI matrix is a well established problem for next POI recommendation, which hinders effective learning of user preferences. Focusing on a more granular extensi…
ARES: Locally Adaptive Reconstruction-based Anomaly Scoring
Adam Goodge, Bryan Hooi, See Kiong Ng +1
How can we detect anomalies: that is, samples that significantly differ from a given set of high-dimensional data, such as images or sensor data? This is a practical problem with n…
LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks
Adam Goodge, Bryan Hooi, See Kiong Ng +1
Many well-established anomaly detection methods use the distance of a sample to those in its local neighbourhood: so-called `local outlier methods', such as LOF and DBSCAN. They ar…