Scholar
Sungryull Sohn
Google Scholar ID: 3Q8LdcYAAAAJ
Research Scientist, LG AI Research
Citations & Impact
Citations
832
H-index
12
i10-index
14
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Paper accepted at CVPR 2025: 'Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents' (forthcoming).
- Paper accepted at ICORES 2025: 'Hierarchical Decomposition Framework for Feasibility-hard Combinatorial Optimization' (Best Student Paper Award, forthcoming).
- Published 'Auto-intent: Automated intent discovery and self-exploration for large language model web agents' in EMNLP Findings 2024.
- Published 'Autoguide: Automated generation and selection of state-aware guidelines for large language model agents' in NeurIPS 2024.
- Published 'Code Models are Zero-shot Precondition Reasoners' in NAACL 2024.
- ArXiv preprint (2024): 'Multiprompter: Cooperative prompt optimization with multi-agent reinforcement learning'.
- Published 'Unsupervised Object Interaction Learning with Counterfactual Dynamics Models' in AAAI 2024.
- Multiple papers at EMNLP 2023, including first-authored 'TOD-Flow: Modeling the Structure of Task-Oriented Dialogues', and others such as 'From Heuristic to Analytic' and 'A Picture is Worth a Thousand Words'.
- Published 'SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations' in NeurIPS 2023.
- Published 'Unsupervised Task Graph Generation from Instructional Video Transcripts' in Findings of ACL.
