Donghyun Kim

Universal Compressed Image Restoration via Codec-Aware Conditioning with Reinforcement Learning AAAI 2026 LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction ACL 2026 Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA EACL 2026 Weakly Supervised Video Scene Graph Generation via Natural Language Supervision ICLR 2025 ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models ICCV 2025 CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning ICCV 2025 MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval ICCV 2025 Large Language Models as Realistic Microservice Trace Generators EMNLP 2025 PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling AAAI 2025 Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation CVPR 2025 RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning AAAI 2025 StitchLLM: Serving LLMs, One Block at a Time ACL 2025 Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning WACV 2025 DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs ECCV 2024 Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection NIPS 2024 LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation CVPR 2024 What How and When Should Object Detectors Update in Continually Changing Test Domains? CVPR 2024 Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval CVPR 2024 Efficient and Versatile Robust Fine-Tuning of Zero-shot Models ECCV 2024 Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection ECCV 2024 MATE: Meet At The Embedding - Connecting Images with Long Texts EMNLP 2024 Adaptive Self-training Framework for Fine-grained Scene Graph Generation ICLR 2024 Guided conditioning with predictive network on score-based diffusion model for speech enhancement INTERSPEECH 2024 Spoken-to-written text conversion with Large Language Model INTERSPEECH 2024 Grafting Vision Transformers WACV 2024 Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models NIPS 2023 Going Beyond Nouns With Vision & Language Models Using Synthetic Data ICCV 2023 SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap ICCV 2023 CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation ICCV 2023 Persona Expansion with Commonsense Knowledge for Diverse and Consistent Response Generation EACL 2023 Towards Efficient Image Compression Without Autoregressive Models NIPS 2023 Concept-based Persona Expansion for Improving Diversity of Persona-Grounded Dialogue EACL 2023 Learning Human Action Recognition Representations Without Real Humans NIPS 2023 ConStruct-VL: Data-Free Continual Structured VL Concepts Learning CVPR 2023 CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning CVPR 2023 A Unified Framework for Domain Adaptive Pose Estimation ECCV 2022 A Broad Study of Pre-training for Domain Generalization and Adaptation ECCV 2022 Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances NAACL 2022 Active Learning on Pre-trained Language Model with Task-Independent Triplet Loss AAAI 2022 BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents AAAI 2022 Learning Cross-Modal Contrastive Features for Video Domain Adaptation ICCV 2021 CDS: Cross-Domain Self-Supervised Pre-Training ICCV 2021 Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density ICCV 2021 Learning to Jump from Pixels CORL 2021 OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization NIPS 2021 MULE: Multimodal Universal Language Embedding AAAI 2020 Unsupervised Attributed Multiplex Network Embedding AAAI 2020 Multi-way Encoding for Robustness WACV 2020 Universal Domain Adaptation through Self Supervision NIPS 2020 Learning to Scale Multilingual Representations for Vision-Language Tasks ECCV 2020 Semi-Supervised Domain Adaptation via Minimax Entropy ICCV 2019 Conversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues NAACL 2019 Excitation Backprop for RNNs CVPR 2018 Speakers’ Intention Prediction Using Statistics of Multi-level Features in a Schedule Management Domain ACL 2008