News

1 paper accepted to ICML!

Generative Visual Code Mobile World Models

2 papers accepted to ACL 2026! (1 main, 1 findings)

Main:

MERIT Feedback Elicits Better Bargaining in LLM Negotiators

Findings:

Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses (Findings)

5 papers accepted to ICLR 2026!

2 papers accepted to AISTATS 2026!

1st place winner in the AI Frontier Challenge at KAIA 2025! (한국인공지능학회)

Team: Sungnyun Kim, Sungwoo Cho

Task: Speech dialogue enhancement under extreme noise environments

6 papers accepted to NeurIPS 2025! (1 spotlight)

1 paper accepted to ICCV 2025!

MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation

4 papers accepted to ICML 2025! (1 oral)

9 papers accepted to ICLR 2025! (7 main, 2 workshop)

Main:

Workshop:

1 paper accepted to AISTATS 2025!

Bayesian Principles Improve Prompt Learning in Vision-Language Models

2 papers accepted to NAACL 2025! (1 main, 1 findings)

Main:

C^2: Scalable Auto-Feedback for LLM-based Chart Generation

Findings:

MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty

1 paper at QIFK 2024 selected as Winner!

DistiLLM: Towards Streamlined Distillation for Large Language Models

1 paper accepted to TMLR!

FLR: Label-Mixture Regularization for Federated Learning with Noisy Labels

8 papers accepted to NeurIPS 2024! (6 main, 2 workshop)

Main:

Workshop:

5 papers accepted to EMNLP 2024! (4 main, 1 findings)

Main:

Findings:

BAPO: Base-Anchored Preference Optimization for Personalized Alignment in Large Language Models

1 paper accepted to TMLR!

Non-backtracking Graph Neural Networks

1 paper at CKAIA 2024 (한국인공지능학회) awarded Best Paper!

A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits

2 papers accepted to ICML 2024!

1 paper at ICASSP 2024 awarded Best Student Paper!

STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models

1 paper accepted to NAACL 2024!

Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models

1 paper accepted to CVPR 2024!

FedSOL: Stabilized Orthogonal Learning in Federated Learning

1 paper accepted to AISTATS 2024!

Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion

2 papers accepted to ICLR 2024 (1 spotlight)!

2 papers accepted to ICASSP 2024.

1 paper accepted to AAAI 2024!

Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning

1 paper at OPODIS 2023 awarded Best Student Paper

Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks

2 papers accepted to OPODIS 2023

4 papers accepted to EMNLP 2023 (1 main, 3 findings)

3 papers accepted to NeurIPS 2023

2 papers accepted to INTERSPEECH 2023.

1 paper accepted to ACL 2023.

Large Language Models Are Reasoning Teachers

2 papers accepted to CVPR 2023.

1 paper accepted to EACL 2023 (findings).

Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective

2 papers accepted to ICLR 2023 (1 spotlight).

2 papers accepted to AISTATS 2023.

1 paper accepted to AAMAS 2023.

Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning

OSI LAB wins 1st place in the Cell Segmentation Challenge at NeurIPS 2022.

Team: Gihun Lee*, Sangmook Kim*, Joonkee Kim*

MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy

3 papers accepted to AAAI 2023 (2 orals).

1 paper at CKAIA 2022 (한국인공지능학회) awarded Best Paper

Near-Optimal Clustering in Block MDPs with Implications on Reward-Free RL

1 paper at JKAIA 2021 (한국인공지능학회) awarded Best Paper and 1 paper awarded Honorable Mention

Best Paper:

MMD-based Fair PCA via Manifold Optimization

Honorable Mention:

Self-Contrastive Learning