Nicholas Sukiennik

Nicholas Sukiennik

Auto-generated profile, based on publicly available information

Nicholas Sukiennik

Tsinghua University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 September 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
JDJingtao Ding
Jingtao Ding
YZYunke Zhang
Yunke Zhang
YSYu Shang
Yu Shang
YZYuheng Zhang
Yuheng Zhang
ZZZefang Zong
Zefang Zong
YLYong Li
Yong Li
The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general intelligence. This survey offers a comprehensive review of the literature on world models. Generally, world models are regarded as tools for either understanding the present state of the world or predicting its future dynamics. This review presents a systematic categorization of world models, emphasizing two primary functions: (1) constructing internal representations to understand the mechanisms of the world, and (2) predicting future states to simulate and guide decision-making. Initially, we examine the current progress in these two categories. We then explore the application of world models in key domains, including autonomous driving, robotics, and social simulacra, with a focus on how each domain utilizes these aspects. Finally, we outline key challenges and provide insights into potential future research directions. We summarize the representative articles along with their code repositories in https://github.com/tsinghua-fib-lab/World-Model .

13 May 2024
Verified
Conference Paper
Open access
NSNicholas Sukiennik
Nicholas Sukiennik
CGChen Gao
Chen Gao
NLNian Li
Nian Li
Filter bubbles have been studied extensively within the context of online content platforms due to their potential to cause undesirable outcomes such as user dissatisfaction or polarization. With the rise of short-video platforms, the filter bubble has been given extra attention because these platforms rely on an unprecedented use of the recommender system to provide relevant content. In our work, we investigate the deep filter bubble, which refers to the user being exposed to narrow content within their broad interests. We accomplish this using one-year interaction data from a top short-video platform in China, which includes hierarchical data with three levels of categories for each video. We formalize our definition of a "deep" filter bubble within this context, and then explore various correlations within the data: first understanding the evolution of the deep filter bubble over time, and later revealing some of the factors that give rise to this phenomenon, such as specific categories, user demographics, and feedback type. We observe that while the overall proportion of users in a filter bubble remains largely constant over time, the depth composition of their filter bubble changes. In addition, we find that some demographic groups that have a higher likelihood of seeing narrower content and implicit feedback signals can lead to less bubble formation. Finally, we propose some ways in which recommender systems can be designed to reduce the risk of a user getting caught in a bubble.

12 November 2026 in ACM Computing Surveys
Verified
Journal Article
Open access
JWJing Yi Wang
Jing Yi Wang
NSNicholas Sukiennik
Nicholas Sukiennik
TLTong Li
Tong Li
WSWeikang Su
Weikang Su
QHQianyue Hao
Qianyue Hao
YLYong Li
Yong Li
The rapid evolution of large language models (LLMs) has positioned them as powerful computational instruments for human-centered research and applications, spanning tasks involving cognition, decision-making, and social interaction. This survey examines LLMs from a human-centric perspective organized around individual and collective levels. We first review LLM competencies across perception, analysis, integration, execution, and social interaction, highlighting both their demonstrated capabilities and the evaluation conditions under which these capabilities are observed. We then explore how LLMs are used across behavioral science, psychology, linguistics, political science, economics, and sociology as research tools, behavioral simulators, and objects of inquiry, covering both individual behavior and collective social processes. Finally, we identify challenges and future research directions, such as improving LLM adaptability, affective-to-behavior evaluation, and cultural sensitivity, while addressing inherent biases and enhancing frameworks for human-AI collaboration. This survey aims to provide a foundational understanding of LLMs from a human-centric perspective, offering insights into their current capabilities and potential for future development.

15 November 2026 in ACM Transactions on the Web
Verified
Journal Article
Open access
NSNicholas Sukiennik
Nicholas Sukiennik
CGChen Gao
Chen Gao
YZYu Zheng
Yu Zheng
QLQun Luo
Qun Luo
PCPeixuan Chen
Peixuan Chen
YLYong Li
Yong Li
Efforts to improve diversity in recommendations typically come at a cost of accuracy. While several works have proposed methods to overcome this tradeoff, they neglect the unique challenges of short-video platforms: extreme long-tail distributions and hierarchical category structures with multiple granularity levels. Meanwhile, graph neural networks have become the state-of-the-art for recommendation because of their ability to achieve collaborative filtering and learn higher-order relationships between users and items. We therefore aim to unlock the capabilities of GNNs for personalization to adapt diversity to individual user preferences and overcome the accuracy-diversity dilemma in short-video recommendation. In this work, we identify two dimensions of diversity preferences–validated by psychological theory and readily inferable from interaction data and modeled using graph neighbor sampling: user preferences for diverse content across category levels, and preferences for fine-grained diversity within broad-level interests. We integrate these dimensions directly into the graph propagation process through neighbor sampling, enabling the model to dynamically balance exploration of diverse categories with exploitation of user preferences during training. We also employ a curriculum training strategy that schedules exposure to items based on popularity-based hardness to determine how this scheduling improves the latent representations of long-tail items and mitigates the accuracy-diversity tradeoff. Through extensive experiments against both standard graph and state-of-the-art graph-based diversified recommendation baselines, we show that our solution achieves superior balance between diversity and accuracy on datasets with extreme long-tail distributions while outperforming state-of-the-art methods at deeper levels of the category hierarchy.