Chanyeol Choi
Research Subjects
Chanyeol Choi has a total of 264 co-authors. Here are the top co-authors by number of shared publications:
- Jeehwan Kim
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA
13 shared publications - Hyunseok Kim
Department of Materials Science and Engineering, University of Illinois Urbana-Champaign, Urbana, USA
8 shared publications Sang-Hoon Bae
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
8 shared publications- Yongjae Lee
UNIST, Ulsan, Republic of Korea
7 shared publications - Chee Wei Wong
Department of Electrical and Computer Engineering Fang Lu Mesoscopic Optics and Quantum Electronics Laboratory University of California Los Angeles
6 shared publications Jaeyong Lee
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
6 shared publications
Latest Publications
- Open Access
- 13 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 973-981
From Hindsight to Foresight: Adapting Reusable Reasoning Structures from Recurring Financial Events
- 13 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 973-981
Open AccessFrom Hindsight to Foresight: Adapting Reusable Reasoning Structures from Recurring Financial Events
- Open Access
- 19 September 2026
- Published by Elsevier in SSRN Electronic Journal
From Hindsight to Foresight: Adapting Reusable Reasoning Structures from Recurring Financial Events
Forecasting real-world events requires reasoning under uncertainty from information available at a fixed cutoff. Recent work has improved how large language models (LLMs) retrieve evidence and produce probabilistic forecasts, but each question is treated independently even when similar events recur. Resolved occurrences carry experience for later forecasts, yet past outcomes and case summaries do not preserve the relationships that made an earlier occurrence informative. We develop ReFoRM (Recurrent-event Forecasting with Reasoning Memory), which organizes reasoning from resolved events into predictive paths, retrieves relevant paths for a later occurrence, and reconstructs their relations using evidence at the new forecast cutoff. We evaluate ReFoRM on the Recurring Financial Events Set, which contains 300 questions across 40 recurring financial event families and uses earlier occurrences as hindsight for 100 forecast targets. Across five LLMs and six baselines, ReFoRM improves categorical and probabilistic forecasting performance. Further analyses show that validating historical relations with current evidence and reconstructing them enhances forecasting. Reasoning evaluation also demonstrates stronger evidence grounding, logical validity, and mechanism specificity.
- 19 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFrom Hindsight to Foresight: Adapting Reusable Reasoning Structures from Recurring Financial Events
Forecasting real-world events requires reasoning under uncertainty from information available at a fixed cutoff. Recent work has improved how large language models (LLMs) retrieve evidence and produce probabilistic forecasts, but each question is treated independently even when similar events recur. Resolved occurrences carry experience for later forecasts, yet past outcomes and case summaries do not preserve the relationships that made an earlier occurrence informative. We develop ReFoRM (Recurrent-event Forecasting with Reasoning Memory), which organizes reasoning from resolved events into predictive paths, retrieves relevant paths for a later occurrence, and reconstructs their relations using evidence at the new forecast cutoff. We evaluate ReFoRM on the Recurring Financial Events Set, which contains 300 questions across 40 recurring financial event families and uses earlier occurrences as hindsight for 100 forecast targets. Across five LLMs and six baselines, ReFoRM improves categorical and probabilistic forecasting performance. Further analyses show that validating historical relations with current evidence and reconstructing them enhances forecasting. Reasoning evaluation also demonstrates stronger evidence grounding, logical validity, and mechanism specificity.
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 632-637
FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 632-637
Open AccessFinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 638-646
FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 638-646
Open AccessFinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 150-158
Your AI, Not Your View: The Bias of LLMs in Investment Analysis
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 150-158
Open AccessYour AI, Not Your View: The Bias of LLMs in Investment Analysis
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6912-6915
Advances in Financial AI: Innovations, Risk, and Responsibility in the Era of LLMs
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6912-6915
Open AccessAdvances in Financial AI: Innovations, Risk, and Responsibility in the Era of LLMs
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4090-4093
Information Retrieval in Finance: Industry and Academic Perspectives on Innovation
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4090-4093
Open AccessInformation Retrieval in Finance: Industry and Academic Perspectives on Innovation
- Top Cited Papers
- 27 November 2023
- Published by Springer Nature in Nature Materials
- Vol. 22 (12) , 1470-1477
Monolithic 3D integration of 2D materials-based electronics towards ultimate edge computing solutions
Three-dimensional (3D) hetero-integration technology is poised to revolutionize the field of electronics by stacking functional layers vertically, thereby creating novel 3D circuity architectures with high integration density and unparalleled multifunctionality. However, the conventional 3D integration technique involves complex wafer processing and intricate interlayer wiring. Here we demonstrate monolithic 3D integration of two-dimensional, material-based artificial intelligence (AI)-processing hardware with ultimate integrability and multifunctionality. A total of six layers of transistor and memristor arrays were vertically integrated into a 3D nanosystem to perform AI tasks, by peeling and stacking of AI processing layers made from bottom-up synthesized two-dimensional materials. This fully monolithic-3D-integrated AI system substantially reduces processing time, voltage drops, latency and footprint due to its densely packed AI processing layers with dense interlayer connectivity. The successful demonstration of this monolithic-3D-integrated AI system will not only provide a material-level solution for hetero-integration of electronics, but also pave the way for unprecedented multifunctional computing hardware with ultimate parallelism.
- 27 November 2023
- Published by Springer Nature in Nature Materials
- Vol. 22 (12) , 1470-1477
Top Cited PapersMonolithic 3D integration of 2D materials-based electronics towards ultimate edge computing solutions
Three-dimensional (3D) hetero-integration technology is poised to revolutionize the field of electronics by stacking functional layers vertically, thereby creating novel 3D circuity architectures with high integration density and unparalleled multifunctionality. However, the conventional 3D integration technique involves complex wafer processing and intricate interlayer wiring. Here we demonstrate monolithic 3D integration of two-dimensional, material-based artificial intelligence (AI)-processing hardware with ultimate integrability and multifunctionality. A total of six layers of transistor and memristor arrays were vertically integrated into a 3D nanosystem to perform AI tasks, by peeling and stacking of AI processing layers made from bottom-up synthesized two-dimensional materials. This fully monolithic-3D-integrated AI system substantially reduces processing time, voltage drops, latency and footprint due to its densely packed AI processing layers with dense interlayer connectivity. The successful demonstration of this monolithic-3D-integrated AI system will not only provide a material-level solution for hetero-integration of electronics, but also pave the way for unprecedented multifunctional computing hardware with ultimate parallelism.
- 20 March 2023
- Published by Springer Nature in Nature Nanotechnology
- Vol. 18 (5) , 464-470
High-throughput manufacturing of epitaxial membranes from a single wafer by 2D materials-based layer transfer process
Layer transfer techniques have been extensively explored for semiconductor device fabrication as a path to reduce costs and to form heterogeneously integrated devices. These techniques entail isolating epitaxial layers from an expensive donor wafer to form freestanding membranes. However, current layer transfer processes are still low-throughput and too expensive to be commercially suitable. Here we report a high-throughput layer transfer technique that can produce multiple compound semiconductor membranes from a single wafer. We directly grow two-dimensional (2D) materials on III–N and III–V substrates using epitaxy tools, which enables a scheme comprised of multiple alternating layers of 2D materials and epilayers that can be formed by a single growth run. Each epilayer in the multistack structure is then harvested by layer-by-layer mechanical exfoliation, producing multiple freestanding membranes from a single wafer without involving time-consuming processes such as sacrificial layer etching or wafer polishing. Moreover, atomic-precision exfoliation at the 2D interface allows for the recycling of the wafers for subsequent membrane production, with the potential for greatly reducing the manufacturing cost.
- 20 March 2023
- Published by Springer Nature in Nature Nanotechnology
- Vol. 18 (5) , 464-470
High-throughput manufacturing of epitaxial membranes from a single wafer by 2D materials-based layer transfer process
Layer transfer techniques have been extensively explored for semiconductor device fabrication as a path to reduce costs and to form heterogeneously integrated devices. These techniques entail isolating epitaxial layers from an expensive donor wafer to form freestanding membranes. However, current layer transfer processes are still low-throughput and too expensive to be commercially suitable. Here we report a high-throughput layer transfer technique that can produce multiple compound semiconductor membranes from a single wafer. We directly grow two-dimensional (2D) materials on III–N and III–V substrates using epitaxy tools, which enables a scheme comprised of multiple alternating layers of 2D materials and epilayers that can be formed by a single growth run. Each epilayer in the multistack structure is then harvested by layer-by-layer mechanical exfoliation, producing multiple freestanding membranes from a single wafer without involving time-consuming processes such as sacrificial layer etching or wafer polishing. Moreover, atomic-precision exfoliation at the 2D interface allows for the recycling of the wafers for subsequent membrane production, with the potential for greatly reducing the manufacturing cost.
- 22 September 2022
- Published by Springer Nature in Nature Nanotechnology
- Vol. 17 (10) , 1054-1059
Graphene nanopattern as a universal epitaxy platform for single-crystal membrane production and defect reduction
Heterogeneous integration of single-crystal materials offers great opportunities for advanced device platforms and functional systems1. Although substantial efforts have been made to co-integrate active device layers by heteroepitaxy, the mismatch in lattice polarity and lattice constants has been limiting the quality of the grown materials2. Layer transfer methods as an alternative approach, on the other hand, suffer from the limited availability of transferrable materials and transfer-process-related obstacles3. Here, we introduce graphene nanopatterns as an advanced heterointegration platform that allows the creation of a broad spectrum of freestanding single-crystalline membranes with substantially reduced defects, ranging from non-polar materials to polar materials and from low-bandgap to high-bandgap semiconductors. Additionally, we unveil unique mechanisms to substantially reduce crystallographic defects such as misfit dislocations, threading dislocations and antiphase boundaries in lattice- and polarity-mismatched heteroepitaxial systems, owing to the flexibility and chemical inertness of graphene nanopatterns. More importantly, we develop a comprehensive mechanics theory to precisely guide cracks through the graphene layer, and demonstrate the successful exfoliation of any epitaxial overlayers grown on the graphene nanopatterns. Thus, this approach has the potential to revolutionize the heterogeneous integration of dissimilar materials by widening the choice of materials and offering flexibility in designing heterointegrated systems.
- 22 September 2022
- Published by Springer Nature in Nature Nanotechnology
- Vol. 17 (10) , 1054-1059
Graphene nanopattern as a universal epitaxy platform for single-crystal membrane production and defect reduction
Heterogeneous integration of single-crystal materials offers great opportunities for advanced device platforms and functional systems1. Although substantial efforts have been made to co-integrate active device layers by heteroepitaxy, the mismatch in lattice polarity and lattice constants has been limiting the quality of the grown materials2. Layer transfer methods as an alternative approach, on the other hand, suffer from the limited availability of transferrable materials and transfer-process-related obstacles3. Here, we introduce graphene nanopatterns as an advanced heterointegration platform that allows the creation of a broad spectrum of freestanding single-crystalline membranes with substantially reduced defects, ranging from non-polar materials to polar materials and from low-bandgap to high-bandgap semiconductors. Additionally, we unveil unique mechanisms to substantially reduce crystallographic defects such as misfit dislocations, threading dislocations and antiphase boundaries in lattice- and polarity-mismatched heteroepitaxial systems, owing to the flexibility and chemical inertness of graphene nanopatterns. More importantly, we develop a comprehensive mechanics theory to precisely guide cracks through the graphene layer, and demonstrate the successful exfoliation of any epitaxial overlayers grown on the graphene nanopatterns. Thus, this approach has the potential to revolutionize the heterogeneous integration of dissimilar materials by widening the choice of materials and offering flexibility in designing heterointegrated systems.