J. D. Zamfirescu-Pereira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
J. D. Zamfirescu-Pereira has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Bjoern Hartmann
University of California, Berkeley, Berkeley, CA, USA
9 shared publications - John DeNero
University of California, Berkeley, Berkeley, CA, USA
7 shared publications - Narges Norouzi
University of California, Berkeley, Berkeley, CA, USA
6 shared publications - Abigail O'NEill
University of California, Berkeley, Berkeley, CA, USA
4 shared publications - Qian Yang
Cornell University, Ithaca, USA
4 shared publications - Samantha Boatright Smith
University of California, Berkeley, Berkeley, CA, USA
4 shared publications
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-23
How Notations Evolve: A Historical Analysis with Implications for Supporting User-Defined Abstractions
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Open AccessHow Notations Evolve: A Historical Analysis with Implications for Supporting User-Defined Abstractions
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Herding CATs: Making Sense of Creative Activity Traces
This workshop aims to advance the analysis of creative activity traces, particularly those captured through user interaction with software creativity support tools (CSTs). Traces of creative activity constitute a rich resource for identifying the impacts of CSTs—especially AI-based CSTs—on the creative process, and may also inform general-purpose process theories of creativity. Several new approaches to making sense of these traces have been introduced in the past few years, but many of these approaches have emerged from largely disjoint research communities, hindering the development of a shared analytical toolkit. We propose to gather HCI and creativity researchers, including proponents of several different trace analysis techniques, to sketch out a technique design space to guide future empirically grounded research on creativity support.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessHerding CATs: Making Sense of Creative Activity Traces
This workshop aims to advance the analysis of creative activity traces, particularly those captured through user interaction with software creativity support tools (CSTs). Traces of creative activity constitute a rich resource for identifying the impacts of CSTs—especially AI-based CSTs—on the creative process, and may also inform general-purpose process theories of creativity. Several new approaches to making sense of these traces have been introduced in the past few years, but many of these approaches have emerged from largely disjoint research communities, hindering the development of a shared analytical toolkit. We propose to gather HCI and creativity researchers, including proponents of several different trace analysis techniques, to sketch out a technique design space to guide future empirically grounded research on creativity support.
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 699-716
"Un-default" Behavior Tuning: Specifying Model Behavior outside the Norm with LLM Self-Playing and Self-Improving
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 699-716
Open Access"Un-default" Behavior Tuning: Specifying Model Behavior outside the Norm with LLM Self-Playing and Self-Improving
- Open Access
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1455-1456
Misconception-Aware LLM Programming Tutor: Lessons Learned from Student-Tutor Interactions
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1455-1456
Open AccessMisconception-Aware LLM Programming Tutor: Lessons Learned from Student-Tutor Interactions
- Open Access
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1453-1454
Instructors' Perspectives on LLM-Generated Programming Formative Feedback
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1453-1454
Open AccessInstructors' Perspectives on LLM-Generated Programming Formative Feedback
- Open Access
- 21 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 78-84
A Knowledge-Component-Based Methodology for Evaluating AI Assistants
- 21 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 78-84
Open AccessA Knowledge-Component-Based Methodology for Evaluating AI Assistants
- Top Cited PapersOpen Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Beyond Code Generation: LLM-supported Exploration of the Program Design Space
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Top Cited PapersOpen AccessBeyond Code Generation: LLM-supported Exploration of the Program Design Space
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Rambler in the Wild: A Diary Study of LLM-Assisted Writing With Speech
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessRambler in the Wild: A Diary Study of LLM-Assisted Writing With Speech
- Open Access
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1669-1670
Pensieve Discuss: Scalable Small-Group CS Tutoring System with AI
Small-group tutoring in Computer Science (CS) is effective, but presents the challenge of providing a dedicated tutor for each group and encouraging collaboration among group members at scale. We present Pensieve Discuss, a software platform that integrates synchronous editing for scaffolded programming problems with online human and AI tutors, designed to improve student collaboration and experience during group tutoring sessions. Our semester-long deployment to CS61A at UC Berkeley demonstrated consistently high collaboration rates, positive feedback about the AI tutor's helpfulness, and increased satisfaction with the group tutoring experience. The use of our system was preferred over an interface lacking AI tutors and synchronous editing capabilities. Our experiences suggest that small-group tutoring sessions are an important avenue for future research in educational AI.
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1669-1670
Open AccessPensieve Discuss: Scalable Small-Group CS Tutoring System with AI
Small-group tutoring in Computer Science (CS) is effective, but presents the challenge of providing a dedicated tutor for each group and encouraging collaboration among group members at scale. We present Pensieve Discuss, a software platform that integrates synchronous editing for scaffolded programming problems with online human and AI tutors, designed to improve student collaboration and experience during group tutoring sessions. Our semester-long deployment to CS61A at UC Berkeley demonstrated consistently high collaboration rates, positive feedback about the AI tutor's helpfulness, and increased satisfaction with the group tutoring experience. The use of our system was preferred over an interface lacking AI tutors and synchronous editing capabilities. Our experiences suggest that small-group tutoring sessions are an important avenue for future research in educational AI.
- Open Access
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1565-1566
From Code to Concepts: Textbook-Driven Knowledge Tracing with LLMs in CS1
Gauging a student's understanding of course concepts, at an arbitrary point during a course, can be challenging. Standardized exams offer only a snapshot of performance rather than a deep understanding of progress. However, with Large Language Models (LLMs) now deployed at scale in CS1 courses, we can track multiple attempts from each student for every homework problem. This data provides insights into how students learn and deploy concepts over time, presenting a unique opportunity to rethink how we track changes in individual student knowledge. Traditional Knowledge Tracing (KT) methods often lack explainability and are computationally expensive. In contrast, our framework leverages an LLM to identify student progress on labeled, problem-level concepts from a student homework code submission. Our initial results show that the student's knowledge state can be dynamically updated. This knowledge state can then be used to provide more targeted, effective feedback and create tailored study materials.
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1565-1566
Open AccessFrom Code to Concepts: Textbook-Driven Knowledge Tracing with LLMs in CS1
Gauging a student's understanding of course concepts, at an arbitrary point during a course, can be challenging. Standardized exams offer only a snapshot of performance rather than a deep understanding of progress. However, with Large Language Models (LLMs) now deployed at scale in CS1 courses, we can track multiple attempts from each student for every homework problem. This data provides insights into how students learn and deploy concepts over time, presenting a unique opportunity to rethink how we track changes in individual student knowledge. Traditional Knowledge Tracing (KT) methods often lack explainability and are computationally expensive. In contrast, our framework leverages an LLM to identify student progress on labeled, problem-level concepts from a student homework code submission. Our initial results show that the student's knowledge state can be dynamically updated. This knowledge state can then be used to provide more targeted, effective feedback and create tailored study materials.