Minsu Kim

25

Papers

138

Total Citations

Papers (25)

Local Search GFlowNets

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

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

Adaptive teachers for amortized samplers

Generative Flows on Synthetic Pathway for Drug Design

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

Non-Adaptive Adversarial Face Generation

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

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

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

Learning Canonical 3D Object Representation for Fine-Grained Recognition

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

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

Speaker-Adaptive Lip Reading with User-Dependent Padding

Mixture of Submodules for Domain Adaptive Person Search

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

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

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

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

Learning to Scale Logits for Temperature-Conditional GFlowNets

Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation

Lip to Speech Synthesis with Visual Context Attentional GAN

Learning Collaborative Policies to Solve NP-hard Routing Problems

Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization

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