Minsu Kim

papers

818

total citations

papers (26)

Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring

CVPR 2023arXiv

citations

Local Search GFlowNets

ICLR 2024arXiv

citations

PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification

CVPR 2023arXiv

citations

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

ICLR 2025arXiv

citations

Learning Energy Decompositions for Partial Inference in GFlowNets

ICLR 2024arXiv

citations

Learning to Scale Logits for Temperature-Conditional GFlowNets

ICML 2024arXiv

citations

Speaker-Adaptive Lip Reading with User-Dependent Padding

ECCV 2022arXiv

citations

Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge

ICCV 2023arXiv

citations

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

NEURIPS 2023arXiv

citations

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

AAAI 2024arXiv

citations

Adaptive teachers for amortized samplers

ICLR 2025arXiv

citations

Generative Flows on Synthetic Pathway for Drug Design

ICLR 2025arXiv

citations

AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation

CVPR 2024arXiv

citations

Learning Canonical 3D Object Representation for Fine-Grained Recognition

ICCV 2021arXiv

citations

Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation

CVPR 2020arXiv

citations

Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization

ICML 2024arXiv

citations

VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection

ECCV 2022arXiv

citations

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

ICCV 2025arXiv

citations

T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning

CVPR 2025arXiv

citations

Non-Adaptive Adversarial Face Generation

NEURIPS 2025arXiv

citations

Mixture of Submodules for Domain Adaptive Person Search

CVPR 2025

citations

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors

ICCV 2025arXiv

citations

Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face Video

ICCV 2021

citations

Minsu Kim

papers (26)

Learning Collaborative Policies to Solve NP-hard Routing Problems

Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization

Lip to Speech Synthesis with Visual Context Attentional GAN

Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring

Local Search GFlowNets

PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

Learning Energy Decompositions for Partial Inference in GFlowNets

Learning to Scale Logits for Temperature-Conditional GFlowNets

Speaker-Adaptive Lip Reading with User-Dependent Padding

Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

Adaptive teachers for amortized samplers

Generative Flows on Synthetic Pathway for Drug Design

AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation

Learning Canonical 3D Object Representation for Fine-Grained Recognition

Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation

Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization

VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning

Non-Adaptive Adversarial Face Generation

Mixture of Submodules for Domain Adaptive Person Search

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors

Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face Video

papers (26)

Learning Collaborative Policies to Solve NP-hard Routing Problems

Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization

Lip to Speech Synthesis with Visual Context Attentional GAN

Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring

Local Search GFlowNets

PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

Learning Energy Decompositions for Partial Inference in GFlowNets

Learning to Scale Logits for Temperature-Conditional GFlowNets

Speaker-Adaptive Lip Reading with User-Dependent Padding

Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context

Adaptive teachers for amortized samplers

Generative Flows on Synthetic Pathway for Drug Design

AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation

Learning Canonical 3D Object Representation for Fine-Grained Recognition

Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation

Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization

VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning

Non-Adaptive Adversarial Face Generation

Mixture of Submodules for Domain Adaptive Person Search

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors

Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face Video