116 citations · 175 across the 24 of their papers we have counts for
24 papers
Feedback Adaptation for Retrieval-Augmented Generation
Jihwan Bang, Seunghan Yang, Kyuhong Shim +3
Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Exi…
Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG
Jihwan Bang, Juntae Lee, Seunghan Yang +1
Multi-hop retrieval-augmented generation (RAG) is a promising strategy for complex reasoning, yet existing iterative prompting approaches remain inefficient. They often regenerate…
CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM
Juntae Lee, Jihwan Bang, Seunghan Yang +1
We present CIFLEX (Contextual Instruction Flow for Sub-task Execution), which is a novel execution system for efficient sub-task handling in multi-turn interactions with a single o…
Learning Contextual Retrieval for Robust Conversational Search
Seunghan Yang, Juntae Lee, Jihwan Bang +3
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of con…
Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Device
Juntae Lee, Jihwan Bang, Seunghan Yang +2
Retrieval-augmented generation (RAG) with large language models (LLMs) is especially valuable in specialized domains, where precision is critical. To more specialize the LLMs into…
Feature Diversification and Adaptation for Federated Domain Generalization
Seunghan Yang, Seokeon Choi, Hyunsin Park +3
Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their…
Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference
Jihwan Bang, Juntae Lee, Kyuhong Shim +2
The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory a…
Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data
Seunghan Yang, Byeonggeun Kim, Kyuhong Shim +1
Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords. However, existing KWS datasets are limited in scal…
Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
Sunghyun Park, Seunghan Yang, Jaegul Choo +1
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in…
Progressive Random Convolutions for Single Domain Generalization
Seokeon Choi, Debasmit Das, Sungha Choi +3
Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains. Image augmentation based on Random…
Scalable Weight Reparametrization for Efficient Transfer Learning
Byeonggeun Kim, Jun-Tae Lee, Seunghan yang +1
This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Effic…
Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
Sungha Choi, Seunghan Yang, Seokeon Choi +1
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to allevia…
Personalized Keyword Spotting through Multi-task Learning
Seunghan Yang, Byeonggeun Kim, Inseop Chung +1
Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting us…
Domain Agnostic Few-shot Learning for Speaker Verification
Seunghan Yang, Debasmit Das, Janghoon Cho +2
Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features. To address this pro…
Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting
Byeonggeun Kim, Seunghan Yang, Inseop Chung +1
Keyword spotting is the task of detecting a keyword in streaming audio. Conventional keyword spotting targets predefined keywords classification, but there is growing attention in…
Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification
Byeonggeun Kim, Seunghan Yang, Jangho Kim +3
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance norm…
QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
Byeonggeun Kim, Seunghan Yang, Jangho Kim +1
This technical report describes the details of our TASK1A submission of the DCASE2021 challenge. The goal of the task is to design an audio scene classification system for device-i…
Distribution Estimation to Automate Transformation Policies for Self-Supervision
Seunghan Yang, Debasmit Das, Simyung Chang +2
In recent visual self-supervision works, an imitated classification objective, called pretext task, is established by assigning labels to transformed or augmented input images. The…
Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization
Byeonggeun Kim, Seunghan Yang, Jangho Kim +1
It is a practical research topic how to deal with multi-device audio inputs by a single acoustic scene classification system with efficient design. In this work, we propose Residua…
Robust Federated Learning with Noisy Labels
Seunghan Yang, Hyoungseob Park, Junyoung Byun +1
Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local dat…
Arbitrary Style Transfer using Graph Instance Normalization
Dongki Jung, Seunghan Yang, Jaehoon Choi +1
Style transfer is the image synthesis task, which applies a style of one image to another while preserving the content. In statistical methods, the adaptive instance normalization…
Associative Partial Domain Adaptation
Youngeun Kim, Sungeun Hong, Seunghan Yang +3
Partial Adaptation (PDA) addresses a practical scenario in which the target domain contains only a subset of classes in the source domain. While PDA should take into account both c…
Partial Domain Adaptation Using Graph Convolutional Networks
Seunghan Yang, Youngeun Kim, Dongki Jung +1
Partial domain adaptation (PDA), in which we assume the target label space is included in the source label space, is a general version of standard domain adaptation. Since the targ…
Combinational Class Activation Maps for Weakly Supervised Object Localization
Seunghan Yang, Yoonhyung Kim, Youngeun Kim +1
Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previo…