Sungwoong Kim

Computer Science · Physical Sciences

24h-index3.8kcitations77works0.82yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(18), Advanced Neural Network Applications(14), Multimodal Machine Learning Applications(14), Advanced Image and Video Retrieval Techniques(13), Machine Learning and Data Classification(9)

Publications77 total

Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
arXiv (Cornell University)·2026Open Access
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
arXiv (Cornell University)·2025Open Access
OSPO: Object-centric Self-improving Preference Optimization for Text-to-Image Generation
arXiv (Cornell University)·2025Open Access
Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
arXiv (Cornell University)·2025Open Access
CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
2025
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization
arXiv (Cornell University)·2025· 2 citedOpen Access
Graph-Based 3-Dimensional Spatial Gene Neighborhood Networks of Single Cells in Gels and Tissues
BME Frontiers·2025Open Access
EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
2025· 1 citedOpen Access
VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms
2025Open Access
Evaluation and Prediction of Mechanical Properties According to Welding Methods of Ni 825/A516-70N Clad Plates
Korean Journal of Metals and Materials·2024· 1 citedOpen Access
CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction
arXiv (Cornell University)·2024Open Access
Scalable Multi-Task Transfer Learning for Molecular Property Prediction
arXiv (Cornell University)·2024Open Access
MEVG: Multi-event Video Generation with Text-to-Video Models
Lecture notes in computer science·2024· 7 cited
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
arXiv (Cornell University)·2024Open Access
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
2024· 2 citedOpen Access
Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
IEEE Access·2024Open Access
Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
2024Open Access
MEVG: Multi-event Video Generation with Text-to-Video Models
arXiv (Cornell University)·2023· 1 citedOpen Access
Hexa: Self-Improving for Knowledge-Grounded Dialogue System
arXiv (Cornell University)·2023Open Access
MAGVLT: Masked Generative Vision-and-Language Transformer
2023· 10 cited
page 1 of 4Next →

Frequent Co-authors

Ildoo Kim(11), Chang D. Yoo(10), Taesup Kim(9), Sebastian Nowozin(7), Jongmin Kim(5), Chiheon Kim(5), Daejin Jo(5), Yoshua Bengio(4), Jörg Hendrik Kappes(4), Bjoern Andres(4), Fred A. Hamprecht(4), Christoph Schnörr(4), Dhruv Batra(4), Bernhard X. Kausler(4), Jan Lellmann(4), Nikos Komodakis(4), Carsten Rother(4), Sungbin Lim(4), Ankur Singh(4), Won Il Park(4)