113 citations · 148 across the 10 of their papers we have counts for
12 papers
Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding
Dohyun Kim, Sungjun Han, Hyungguk Kim +4
Autoregressive OCR vision-language models accurately convert document images into text and structured markup, but require one sequential decoding step per output token, limiting in…
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
Hyunjin Seo, Hyeon Hwang, Gyubok Lee +7
The push toward large language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine understanding of biology. However, existing b…
VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design
Hyunjin Seo, Hongjoon Ahn, Jimin Park +16
Protein design aims to compose amino-acid sequences that fold into stable three-dimensional structures while satisfying targeted functional properties. The field is increasingly sh…
Action-Sufficient Goal Representations
Jinu Hyeon, Woobin Park, Hongjoon Ahn +1
In offline goal-conditioned reinforcement learning (GCRL), hierarchical approaches decompose long-horizon tasks into high-level subgoal prediction and low-level action execution. A…
Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
Hongjoon Ahn, Heewoong Choi, Jisu Han +1
Offline goal-conditioned reinforcement learning (GCRL) offers a practical learning paradigm in which goal-reaching policies are trained from abundant state-action trajectory datase…
Listwise Reward Estimation for Offline Preference-based Reinforcement Learning
Heewoong Choi, Sangwon Jung, Hongjoon Ahn +1
In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduce…
Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning
Hongjoon Ahn, Jinu Hyeon, Youngmin Oh +2
We argue that the negative transfer problem occurring when the new task to learn arrives is an important problem that needs not be overlooked when developing effective Continual Re…
Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
Hongjoon Ahn, Yongyi Yang, Quan Gan +2
Heterogeneous graph neural networks (GNNs) achieve strong performance on node classification tasks in a semi-supervised learning setting. However, as in the simpler homogeneous GNN…
SS-IL: Separated Softmax for Incremental Learning
Hongjoon Ahn, Jihwan Kwak, Subin Lim +3
We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predic…
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
Sangwon Jung, Hongjoon Ahn, Sungmin Cha +1
We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based penalties. Ou…
Uncertainty-based Continual Learning with Adaptive Regularization
Hongjoon Ahn, Sungmin Cha, Donggyu Lee +1
We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learni…
Iterative Channel Estimation for Discrete Denoising under Channel Uncertainty
Hongjoon Ahn, Taesup Moon
We propose a novel iterative channel estimation (ICE) algorithm that essentially removes the critical known noisy channel assumption for universal discrete denoising problem. Our a…