39 citations · 50 across the 9 of their papers we have counts for
10 papers
Continually Post-training Small Models via Synthetic Self-distillation
Woosung Koh, Hyunsoo Lee, Kyungjae Lee +4
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. While Self-Distillation Fine-Tunin…
Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
Sungjun Cho, Dasol Hwang, Frederic Sala +3
Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned…
Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
Sungmin Cha, Sungjun Cho, Dasol Hwang +1
Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and co…
Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
Kyungjae Lee, Dasol Hwang, Sunghyun Park +2
Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance o…
Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
Byoungjip Kim, Sungik Choi, Dasol Hwang +2
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources.…
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Sungmin Cha, Sungjun Cho, Dasol Hwang +3
Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sen…
Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning
Sungmin Cha, Sungjun Cho, Dasol Hwang +3
Batch Normalization (BN) and its variants has been extensively studied for neural nets in various computer vision tasks, but relatively little work has been dedicated to studying t…
Point Cloud Augmentation with Weighted Local Transformations
Sihyeon Kim, Sanghyeok Lee, Dasol Hwang +3
Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach…
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
Dasol Hwang, Jinyoung Park, Sunyoung Kwon +3
In recent years, graph neural networks (GNNs) have been widely adopted in the representation learning of graph-structured data and provided state-of-the-art performance in various…
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Dasol Hwang, Jinyoung Park, Sunyoung Kwon +3
Graph neural networks have shown superior performance in a wide range of applications providing a powerful representation of graph-structured data. Recent works show that the repre…