Kyuhong Shim

Orcid: 0000-0002-0123-3100

According to our database¹, Kyuhong Shim authored at least 47 papers between 2017 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models.

[BibT_eX]

[DOI]

CoRR, May, 2026

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models.

[BibT_eX]

[DOI]

CoRR, April, 2026

DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues.

[BibT_eX]

[DOI]

CoRR, April, 2026

Feedback Adaptation for Retrieval-Augmented Generation.

[BibT_eX]

[DOI]

CoRR, April, 2026

Revealing Multi-View Hallucination in Large Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, March, 2026

Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching.

[BibT_eX]

[DOI]

CoRR, March, 2026

Adaptive Capacity Allocation for Vision Language Action Fine-tuning.

[BibT_eX]

[DOI]

CoRR, March, 2026

Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding.

[BibT_eX]

[DOI]

CoRR, March, 2026

Advancing Multi-Robot Networks via MLLM-Driven Sensing, Communication, and Computation: A Comprehensive Survey.

[BibT_eX]

[DOI]

IEEE Commun. Surv. Tutorials, 2026

2025

Evaluating Hallucinations in Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditions.

[BibT_eX]

[DOI]

CoRR, October, 2025

Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs.

[BibT_eX]

[DOI]

CoRR, May, 2025

Voicing Personas: Rewriting Persona Descriptions into Style Prompts for Controllable Text-to-Speech.

[BibT_eX]

[DOI]

Yejin Lee

Jaehoon Kang

Kyuhong Shim

CoRR, May, 2025

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Device.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Learning Primitive Relations for Compositional Zero-Shot Learning.

[BibT_eX]

[DOI]

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Learning Contextual Retrieval for Robust Conversational Search.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Role of Sensing and Computer Vision in 6G Wireless Communications.

[BibT_eX]

[DOI]

IEEE Wirel. Commun., October, 2024

Unlocking Transfer Learning for Open-World Few-Shot Recognition.

[BibT_eX]

[DOI]

CoRR, 2024

Leveraging Adapter for Parameter-Efficient ASR Encoder.

[BibT_eX]

[DOI]

Kyuhong Shim

Jinkyu Lee

Hyunjae Kim

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

InfiniPot: Infinite Context Processing on Memory-Constrained LLMs.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Toward Intelligent Millimeter and Terahertz Communication for 6G: Computer Vision-Aided Beamforming.

[BibT_eX]

[DOI]

IEEE Wirel. Commun., October, 2023

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data.

[BibT_eX]

[DOI]

CoRR, 2023

Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer.

[BibT_eX]

[DOI]

CoRR, 2023

Exploring Attention Map Reuse for Efficient Transformer Neural Networks.

[BibT_eX]

[DOI]

Kyuhong Shim

Jungwook Choi

Wonyong Sung

CoRR, 2023

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data.

[BibT_eX]

[DOI]

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer.

[BibT_eX]

[DOI]

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Depth-Relative Self Attention for Monocular Depth Estimation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Task-Agnostic Open-Set Prototype for Few-Shot Open-Set Recognition.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Image Processing, 2023

Spatial Cross-Attention for Transformer-Based Image Captioning.

[BibT_eX]

[DOI]

Khoa Anh Ngo

Kyuhong Shim

Byonghyo Shim

Proceedings of the IEEE International Conference on Acoustics, 2023

Semantic-Preserving Augmentation for Robust Image-Text Retrieval.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Vision Transformer-Based Feature Extraction for Generalized Zero-Shot Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Korean Tokenization for Beam Search Rescoring in Speech Recognition.

[BibT_eX]

[DOI]

Kyuhong Shim

Hyewon Bae

Wonyong Sung

Proceedings of the International Conference on Electronics, Information, and Communication, 2023

Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers.

[BibT_eX]

[DOI]

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023

2022

Optimization of General Matrix Multiply Library for Ternary Weight for Fast DNN Inference.

[BibT_eX]

[DOI]

J. Signal Process. Syst., 2022

A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition.

[BibT_eX]

[DOI]

Kyuhong Shim

Wonyong Sung

CoRR, 2022

Pseudo-Label-Free Weakly Supervised Semantic Segmentation Using Image Masking.

[BibT_eX]

[DOI]

IEEE Access, 2022

Similarity and Content-based Phonetic Self Attention for Speech Recognition.

[BibT_eX]

[DOI]

Kyuhong Shim

Wonyong Sung

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Understanding the Role of Self Attention for Efficient Speech Recognition.

[BibT_eX]

[DOI]

Kyuhong Shim

Jungwook Choi

Wonyong Sung

Proceedings of the Tenth International Conference on Learning Representations, 2022

Semantic Feature Extraction for Generalized Zero-Shot Learning.

[BibT_eX]

[DOI]

Junhan Kim

Kyuhong Shim

Byonghyo Shim

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

TernGEMM: GEneral Matrix Multiply Library with Ternary Weights for Fast DNN Inference.

[BibT_eX]

[DOI]

Proceedings of the IEEE Workshop on Signal Processing Systems, 2021

Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling.

[BibT_eX]

[DOI]

Proceedings of the 18th International SoC Design Conference, 2021

2017

SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Kyuhong Shim

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...