Irwin King

Does school-based AI education narrow readiness gaps? The role of prior agency-related learning

Siya Liang, King Woon Yau, Helen Meng, Thomas K. F. Chiu et autres

As artificial intelligence (AI) becomes part of everyday learning, preparing students to participate confidently and responsibly in AI-mediated environments is essential. Yet students enter AI classes with different prior agency-related learning experiences, indicated in this study by self-initiated AI learning before school-based …

hk (code pays fourni par la source)

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development

Muzhi Li, Jianpeng Qi, Yihong Wu, Minghao Zhao et autres

Retrieval-augmented generation (RAG) agent development is hindered by the lack of executable ground-truth agent-environment interaction trajectories. Existing datasets provide questions, answers, and evidence, but lack fine-grained supervision for retriever invocation, dynamic planning, and stepwise decision-making. Reinforcement learning offers a potential solution, but …

hk, ca, gb, se (code pays fourni par la source)

LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

Yanyu Chen, Jiyue Jiang, Dianzhi Yu, Zheng Wu et autres

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label Noise via Mimetic Bias, where rewards prioritize statistical likelihood …

hk, cn (code pays fourni par la source)

Hyperbolic Learning for Structured Data, Knowledge, and Memory: A Tutorial

Jiahong Liu, Meng‐Lin Yang, Irwin King

Foundation models are increasingly deployed as agentic data-and-memory systems built on pretrained parameters, retrieval corpora, external knowledge stores, and persistent interaction histories. For the Knowledge Discovery and Data Mining (KDD) community, this matters because recommendation, search, temporal modeling, enterprise knowledge systems, and …

hk (code pays fourni par la source)

Incorporating 3D Structural Information for Activity Cliff Analysis

Zijing Liu, Xinni Zhang, Yankai Chen, Bin Feng et autres

Artificial intelligence has become a crucial tool in drug discovery, excelling in tasks such as molecular property prediction. However, the activity cliff, where a minor structural modification to a molecule leads to a significant change in its biological activity, remains a challenge …

hk, us, cn (code pays fourni par la source)

Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies

Elyas Meguellati, Stefano Civelli, Pietro Bernardelle, Shazia Sadiq et autres

Political advertising plays a pivotal role in shaping public opinion and influencing electoral outcomes, often through subtle persuasive techniques embedded in broader propaganda strategies. Detecting these persuasive elements is crucial for enhancing voter awareness and ensuring transparency in democratic processes. This paper …

au, hk (code pays fourni par la source)

A Survey on Vision--Language--Action Models for Embodied AI

Yueen Ma, Zixing Song, Yuzheng Zhuang, Jianye Hao et autres

Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language models (VLMs), a new category …

hk, gb, cn (code pays fourni par la source)

HC-GLAD: Dual hyperbolic contrastive learning for unsupervised graph-level anomaly detection

Yali Fu, Jiahong Liu, Qianli Xing, Yanyan Wang et autres

cn, hk (code pays fourni par la source)

Generative Archetype-Grounded Item Representations for Sequential Recommendation

Yifan Li, Jiahong Liu, Xinni Zhang, Hao Chen et autres

Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of item representations remains a critical bottleneck. While pre-trained large language models (LLMs) can provide rich semantic representations, existing approaches only rely on …

hk, ca, cn (code pays fourni par la source)

TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents

Yanyu Chen, Jiyue Jiang, Jiahong Liu, Y. X. Zhang et autres

The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics like Pass@1, creating a ''high-score illusion'' that …

hk (code pays fourni par la source)

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

Jindong Li, Yali Fu, Jiahong Liu, L. J. Cao et autres

The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into discrete representations suitable for language-based processing. Discrete tokenization, with vector quantization (VQ) as a central approach, offers both computational efficiency and …

cn, hk, us (code pays fourni par la source)

Towards Practical Automatic Piano Reduction using BERT with Semi-supervised Learning

Wan Ki Wong, Ka Ho To, Chuck-jee Chau, Lucas Wong et autres

In this study, we present a novel automatic piano reduction method with semi-supervised machine learning. Piano reduction is an important music transformation process, which helps musicians and composers as a musical sketch for performances and analysis. The automation of such is a …