19 citations · 48 across the 14 of their papers we have counts for
14 papers
FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation
Sohyun An, Hayeon Lee, Shuibenyang Yuan +4
Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within th…
Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
Sohyun An, Shuibenyang Yuan, Hayeon Lee +2
Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold…
Diffusion-Based Neural Network Weights Generation
Bedionita Soro, Bruno Andreis, Hayeon Lee +4
Transfer learning has gained significant attention in recent deep learning research due to its ability to accelerate convergence and enhance performance on new tasks. However, its…
Co-training and Co-distillation for Quality Improvement and Compression of Language Models
Hayeon Lee, Rui Hou, Jongpil Kim +4
Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resourc…
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models
Hayeon Lee, Rui Hou, Jongpil Kim +3
Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studi…
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
Hayeon Lee, Sohyun An, Minseon Kim +1
Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the kno…
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
Sohyun An, Hayeon Lee, Jaehyeong Jo +2
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existi…
A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search
Stephen Cha, Taehyeon Kim, Hayeon Lee +1
This survey focuses on categorizing and evaluating the methods of supernet optimization in the field of Neural Architecture Search (NAS). Supernet optimization involves training a…
Online Hyperparameter Meta-Learning with Hypergradient Distillation
Hae Beom Lee, Hayeon Lee, Jaewoong Shin +3
Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters. Although such hyperp…
Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
Hayeon Lee, Eunyoung Hyung, Sung Ju Hwang
Despite the success of recent Neural Architecture Search (NAS) methods on various tasks which have shown to output networks that largely outperform human-designed networks, convent…
HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning
Hayeon Lee, Sewoong Lee, Song Chong +1
For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and en…
Task-Adaptive Neural Network Search with Meta-Contrastive Learning
Wonyong Jeong, Hayeon Lee, Gun Park +3
Most conventional Neural Architecture Search (NAS) approaches are limited in that they only generate architectures without searching for the optimal parameters. While some NAS meth…
Learning to Generalize to Unseen Tasks with Bilevel Optimization
Hayeon Lee, Donghyun Na, Hae Beom Lee +1
Recent metric-based meta-learning approaches, which learn a metric space that generalizes well over combinatorial number of different classification tasks sampled from a task distr…
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
Hae Beom Lee, Hayeon Lee, Donghyun Na +4
While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the num…