Tung Sum Thomas Kwok
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tung Sum Thomas Kwok has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Fengran Mo
Université de Montréal, Montréal, Quebec, Canada
2 shared publications - Hailin He
SimpleWay.AI, Chengdu, China
2 shared publications - Huang Jerry
Mila – Quebec AI institute, Montreal, Canada
2 shared publications - Jijun Chi
SimpleWay.AI, Toronto, Canada
2 shared publications - Jingrui Tian
University of California, Los Angeles, Los Angeles, CA, USA
2 shared publications - Ling Zhou
CG Matrix Technology Limited, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 20 October 2026
- Published by MDPI AG in Preprints.org
Data-Centric Recursive Improvement for Foundation Models: A Survey
Data-centric methods are central to foundation model development, but data construction and evaluation have often been treated as separate stages. Recent model-development pipelines increasingly couple the two: evaluation results expose capability gaps and failure modes, which then guide data selection, filtering, synthesis, and post-training interventions that shape the behavior of subsequent model versions. This survey studies this trend as data-centric recursive improvement, with data-evaluation co-evolution as its core mechanism. In this mechanism, evaluation produces diagnostic signals, orchestration determines whether and how these signals should be trusted and used, and execution updates mutable data-related objects. These updated objects are then used in later training, adaptation, retrieval, or memory stages, enabling the system to change in subsequent rounds. The framework centers on three questions: what signal diagnoses the current system, who decides how to act on that signal, and what object is updated to affect the next round. We organize the literature around this signal-decision-update loop, covering feedback signals, control decisions, and data updates across major stages of foundation model development. We further examine failure modes in closed-loop improvement, such as unreliable feedback, feedback overfitting, unstable updates, erosion of data support, and irreproducible system changes. By providing a structured framework for understanding and designing data-evaluation co-evolution, this survey outlines a roadmap toward more adaptive, robust, and accountable foundation model development, where evaluation becomes an active driver of recursive model improvement rather than a passive measure of progress and ultimately sheds light on possible pathways toward Artificial Super Intelligence (ASI), in which a model continually evolve and surpass human-level performance across diverse tasks. All surveyed papers are organized in a public repository https://github.com/zoezou2015/Awesome-Data-Centric-Recursive-Improvement.
- 20 October 2026
- Published by MDPI AG in Preprints.org
Open AccessData-Centric Recursive Improvement for Foundation Models: A Survey
Data-centric methods are central to foundation model development, but data construction and evaluation have often been treated as separate stages. Recent model-development pipelines increasingly couple the two: evaluation results expose capability gaps and failure modes, which then guide data selection, filtering, synthesis, and post-training interventions that shape the behavior of subsequent model versions. This survey studies this trend as data-centric recursive improvement, with data-evaluation co-evolution as its core mechanism. In this mechanism, evaluation produces diagnostic signals, orchestration determines whether and how these signals should be trusted and used, and execution updates mutable data-related objects. These updated objects are then used in later training, adaptation, retrieval, or memory stages, enabling the system to change in subsequent rounds. The framework centers on three questions: what signal diagnoses the current system, who decides how to act on that signal, and what object is updated to affect the next round. We organize the literature around this signal-decision-update loop, covering feedback signals, control decisions, and data updates across major stages of foundation model development. We further examine failure modes in closed-loop improvement, such as unreliable feedback, feedback overfitting, unstable updates, erosion of data support, and irreproducible system changes. By providing a structured framework for understanding and designing data-evaluation co-evolution, this survey outlines a roadmap toward more adaptive, robust, and accountable foundation model development, where evaluation becomes an active driver of recursive model improvement rather than a passive measure of progress and ultimately sheds light on possible pathways toward Artificial Super Intelligence (ASI), in which a model continually evolve and surpass human-level performance across diverse tasks. All surveyed papers are organized in a public repository https://github.com/zoezou2015/Awesome-Data-Centric-Recursive-Improvement.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7757-7768
VeritasFi : An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 7757-7768
Open AccessVeritasFi : An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6144-6152
FinSage: A Multi-aspect RAG System for Financial Filings Question Answering
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6144-6152
Open AccessFinSage: A Multi-aspect RAG System for Financial Filings Question Answering