Sung Ju Hwang

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation CVPR 2026 Unified Multimodal Interleaved Document Representation for Retrieval EACL 2026 UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities ACL 2026 WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning CVPR 2026 A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention ICLR 2025 AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML ICML 2025 Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks ICML 2025 Database-Augmented Query Representation for Information Retrieval EMNLP 2025 Diffusion-based Neural Network Weights Generation ICLR 2025 Efficient Long Context Language Model Retrieval with Compression ACL 2025 Efficient Real-time Refinement of Language Model Text Generation EMNLP 2025 HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models ICLR 2025 Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning ICLR 2025 ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models NAACL 2025 SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models ACL 2025 Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models CVPR 2025 Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching EMNLP 2025 Training Free Exponential Context Extension via Cascading KV Cache ICLR 2025 VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding CVPR 2025 VideoRAG: Retrieval-Augmented Generation over Video Corpus ACL 2025 Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity NAACL 2024 BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation ICML 2024 Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models NAACL 2024 Concept-skill Transferability-based Data Selection for Large Vision-Language Models EMNLP 2024 DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models ICLR 2024 Drug Discovery with Dynamic Goal-aware Fragments ICML 2024 ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning CVPR 2024 EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens ICML 2024 Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes ICML 2024 Graph Generation with Diffusion Mixture ICML 2024 Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models NeurIPS 2024 KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis NeurIPS 2024 Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models NeurIPS 2024 LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs NAACL 2024 One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts ICML 2024 Progressive Fourier Neural Representation for Sequential Video Compilation ICLR 2024 Rethinking Code Refinement: Learning to Judge Code Efficiency EMNLP 2024 SEA: Sparse Linear Attention with Estimated Attention Mask ICLR 2024 Self-Supervised Dataset Distillation for Transfer Learning ICLR 2024 Set-based Neural Network Encoding Without Weight Tying NeurIPS 2024 STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment ICML 2024 A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models ACL 2023 Continual Learners are Incremental Model Generalizers ICML 2023 Direct Fact Retrieval from Knowledge Graphs without Entity Linking ACL 2023 Effective Targeted Attacks for Adversarial Self-Supervised Learning NeurIPS 2023 Exploring Chemical Space with Score-based Out-of-distribution Generation ICML 2023 Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders ICLR 2023 Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations NeurIPS 2023 Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks NeurIPS 2023 Language Detoxification with Attribute-Discriminative Latent Space ACL 2023 Margin-based Neural Network Watermarking ICML 2023 Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets ICLR 2023 On the Soft-Subnetwork for Few-Shot Class Incremental Learning ICLR 2023 Personalized Subgraph Federated Learning ICML 2023 Phrase Retrieval for Open Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning ACL 2023 Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement EACL 2023 Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation ICML 2023 Self-Distillation for Further Pre-training of Transformers ICLR 2023 Self-Supervised Set Representation Learning for Unsupervised Meta-Learning ICLR 2023 Sparse Token Transformer with Attention Back Tracking ICLR 2023 STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection NeurIPS 2023 Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models ICCV 2023 The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation CVPR 2023 ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models Interspeech 2023 Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation ACL 2022 Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization ICML 2022 Consistency Regularization for Adversarial Robustness AAAI 2022 Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching NeurIPS 2022 Forget-free Continual Learning with Winning Subnetworks ICML 2022 Graph Self-supervised Learning with Accurate Discrepancy Learning NeurIPS 2022 KALA: Knowledge-Augmented Language Model Adaptation NAACL 2022 Learning to Generate Inversion-Resistant Model Explanations NeurIPS 2022 Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty ICLR 2022 Model-augmented Prioritized Experience Replay ICLR 2022 MPViT: Multi-Path Vision Transformer for Dense Prediction CVPR 2022 Online Coreset Selection for Rehearsal-based Continual Learning ICLR 2022 Online Hyperparameter Meta-Learning with Hypergradient Distillation ICLR 2022 Representational Continuity for Unsupervised Continual Learning ICLR 2022 Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing AAAI 2022 Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations ICML 2022 Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning ICLR 2022 Set-based Meta-Interpolation for Few-Task Meta-Learning NeurIPS 2022 Set Based Stochastic Subsampling ICML 2022 Skill-based Meta-Reinforcement Learning ICLR 2022 Accurate Learning of Graph Representations with Graph Multiset Pooling ICLR 2021 Adversarial Purification with Score-based Generative Models ICML 2021 Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning AAAI 2021 Cluster-Promoting Quantization With Bit-Drop for Minimizing Network Quantization Loss ICCV 2021 Contrastive Learning with Adversarial Perturbations for Conditional Text Generation ICLR 2021 Edge Representation Learning with Hypergraphs NeurIPS 2021 Federated Continual Learning with Weighted Inter-client Transfer ICML 2021 Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning ICLR 2021 FedMix: Approximation of Mixup under Mean Augmented Federated Learning ICLR 2021 GTA: Graph Truncated Attention for Retrosynthesis AAAI 2021 Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning NeurIPS 2021 Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation NeurIPS 2021 Large-Scale Meta-Learning with Continual Trajectory Shifting ICML 2021 Learning to Generate Noise for Multi-Attack Robustness ICML 2021 Learning to Perturb Word Embeddings for Out-of-distribution QA ACL 2021 Learning to Sample with Local and Global Contexts in Experience Replay Buffer ICLR 2021 Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning ICLR 2021 Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation ICML 2021 Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding NeurIPS 2021 Multi-Domain Knowledge Distillation via Uncertainty-Matching for End-to-End ASR Models Interspeech 2021 Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets ICLR 2021 RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning IJCAI 2021 Task-Adaptive Neural Network Search with Meta-Contrastive Learning NeurIPS 2021 Adversarial Neural Pruning with Latent Vulnerability Suppression ICML 2020 Adversarial Self-Supervised Contrastive Learning NeurIPS 2020 Attribution Preservation in Network Compression for Reliable Network Interpretation NeurIPS 2020 Bootstrapping neural processes NeurIPS 2020 Cost-Effective Interactive Attention Learning with Neural Attention Processes ICML 2020 Deep Mixed Effect Model Using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare AAAI 2020 Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning NeurIPS 2020 Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning NeurIPS 2020 Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs ACL 2020 Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks ICLR 2020 Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction NeurIPS 2020 Meta Dropout: Learning to Perturb Latent Features for Generalization ICLR 2020 Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs Interspeech 2020 MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures NeurIPS 2020 Meta Variance Transfer: Learning to Augment from the Others ICML 2020 Neural Complexity Measures NeurIPS 2020 Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation EMNLP 2020 Scalable and Order-robust Continual Learning with Additive Parameter Decomposition ICLR 2020 Self-supervised Label Augmentation via Input Transformations ICML 2020 Time-Reversal Symmetric ODE Network NeurIPS 2020 Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks ICLR 2020 Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data ACL 2019 LEARNING TO PROPAGATE LABELS: TRANSDUCTIVE PROPAGATION NETWORK FOR FEW-SHOT LEARNING ICLR 2019 Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss CVPR 2019 Learning What and Where to Transfer ICML 2019 Deep Asymmetric Multi-task Feature Learning ICML 2018 DropMax: Adaptive Variational Softmax NeurIPS 2018 Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding NeurIPS 2018 Lifelong Learning with Dynamically Expandable Networks ICLR 2018 Uncertainty-Aware Attention for Reliable Interpretation and Prediction NeurIPS 2018 Combined Group and Exclusive Sparsity for Deep Neural Networks ICML 2017 SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization ICML 2017 Expanding Object Detector's Horizon: Incremental Learning Framework for Object Detection in Videos CVPR 2015 A Unified Semantic Embedding: Relating Taxonomies and Attributes NeurIPS 2014 Analogy-preserving Semantic Embedding for Visual Object Categorization ICML 2013 Semantic Kernel Forests from Multiple Taxonomies NeurIPS 2012 Learning a Tree of Metrics with Disjoint Visual Features NeurIPS 2011