News

2026
2026.06
New preprint: "ModelPinch: Diverse Task Experts Are Dense Even in 4 Parameters"
2026.05
New preprint: "LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring"
2026.05
New preprint: "EduVideoBench: A Knowledge-Skills-Attitude Benchmark for Educational Video Generation"
2026.05
New preprint: "BuddyBench: A Privacy-Constrained Multi-Task Benchmark for Pediatric Social-Communication Personalization"
2026.05
New preprint: "TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation"
2026.05
New preprint: "Reinforcement Learning for Special Education: Aligning LLM Tutors to Diverse Learners"
2026.05
New preprint: "The Tutoring Effectiveness Index: Predicting LLM Math Tutor Quality from Four Conversation Signals"
2026.03
LEAP Lab has moved to Korea University Sejong Campus.
2026.02
New preprint: "Llama-Polya: Instruction Tuning for LLM based on Polya's Problem-solving"
2026.02
New preprint: "ISD-Agent-Bench: A Comprehensive Benchmark for Evaluating LLM-based Instructional Design Agents"
2026.02
New preprint: "Exploring the Role of Automated Feedback in Programming Education: A Systematic Literature Review"
2026.01
New preprint: "Rewarding How Models Think Pedagogically"
2026.01
New preprint: "Pedagogical Alignment for Vision-Language-Action Models"
2026.01
New preprint: "OpenLearnLM Benchmark: Evaluating Knowledge, Skill, and Attitude in Educational LLMs"
2026.01
New preprint: "A Training-Free Large Reasoning Model-based Knowledge Tracing Framework" (Thinking-KT)
2025
2025.11
Paper accepted at CIKM 2025: "Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark"
2025.09
LEAP Lab has been officially launched at Chosun University.