| Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment D Kim, J Kim, K Lee, J Shin The Thirteenth International Conference on Learning Representations, 2025 | 38* | 2025 |
| Accelerating reinforcement learning with value-conditional state entropy exploration D Kim, J Shin, P Abbeel, Y Seo Advances in Neural Information Processing Systems 36, 31811-31830, 2023 | 33 | 2023 |
| Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics D Kim, S Park, H Jang, J Shin, J Kim, Y Seo Advances in Neural Information Processing Systems (NeurIPS) 2025, 2025 | 8 | 2025 |
| Learning to correct for qa reasoning with black-box llms J Kim, D Kim, Y Yang arXiv preprint arXiv:2406.18695, 2024 | 8 | 2024 |
| Visual representation learning with stochastic frame prediction H Jang, D Kim, J Kim, J Shin, P Abbeel, Y Seo arXiv preprint arXiv:2406.07398, 2024 | 8 | 2024 |
| Collaborative LLM Inference via Planning for Efficient Reasoning B Lee, J Lee, D Kim, J Kim, J Shin arXiv preprint arXiv:2506.11578, 2025 | 4 | 2025 |
| Dual-stream diffusion for world-model augmented vision-language-action model J Won, K Lee, H Jang, D Kim, J Shin arXiv preprint arXiv:2510.27607, 2025 | 3 | 2025 |
| Verifier-free Test-Time Sampling for Vision Language Action Models S Jang, D Kim, C Kim, Y Kim, J Shin arXiv preprint arXiv:2510.05681, 2025 | 1 | 2025 |
| Contrastive Representation Regularization for Vision-Language-Action Models T Kim, J Lee, M Koo, D Kim, K Lee, C Kim, Y Seo, J Shin arXiv preprint arXiv:2510.01711, 2025 | | 2025 |
| Training-free LLM Verification via Recycling Few-shot Examples D Lee, J Hong, D Kim, J Kim arXiv preprint arXiv:2506.17251, 2025 | | 2025 |
| Debiasing online preference learning via preference feature preservation D Kim, J Yoon, J Shin, J Kim arXiv preprint arXiv:2506.11098, 2025 | | 2025 |
Jinwoo ShinICT Endowed Chair ProfessorVerified email at kaist.ac.kr
