Jinwoo Shin

73

Papers

444

Total Citations

Papers (73)

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Discovering and Mitigating Visual Biases through Keyword Explanation

DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

Querying Easily Flip-flopped Samples for Deep Active Learning

Gauging Variational Inference

NeurIPS 2017arXiv

Adversarial Robustification via Text-to-Image Diffusion Models

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction

Test-Time Adaptation with Binary Feedback

Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

Video Probabilistic Diffusion Models in Projected Latent Space

Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild

Co2L: Contrastive Continual Learning

K-Centered Patch Sampling for Efficient Video Recognition

Minimum Weight Perfect Matching via Blossom Belief Propagation

NeurIPS 2015arXiv

Synthesis of MCMC and Belief Propagation

Closest Neighbors are Harmful for Lightweight Masked Auto-encoders

Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization

Visual Representation Learning with Stochastic Frame Prediction

Controllable Human Image Generation with Personalized Multi-Garments

Data-Efficient Molecular Generation with Hierarchical Textual Inversion

Hierarchical Novelty Detection for Visual Object Recognition

Regularizing Class-Wise Predictions via Self-Knowledge Distillation

M2m: Imbalanced Classification via Major-to-Minor Translation

Quality-Agnostic Image Recognition via Invertible Decoder

Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning

Patch-Level Representation Learning for Self-Supervised Vision Transformers

Self-Supervised Dense Consistency Regularization for Image-to-Image Translation

IFSeg: Image-Free Semantic Segmentation via Vision-Language Model

Learning Large-scale Neural Fields via Context Pruned Meta-Learning

Collaborative Score Distillation for Consistent Visual Editing

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Large-scale log-determinant computation through stochastic Chebyshev expansions

Optimality of Belief Propagation for Crowdsourced Classification

Faster Greedy MAP Inference for Determinantal Point Processes

Confident Multiple Choice Learning

Bucket Renormalization for Approximate Inference

Learning What and Where to Transfer

Training CNNs with Selective Allocation of Channels

Robust Inference via Generative Classifiers for Handling Noisy Labels

Spectral Approximate Inference

Learning to Specialize with Knowledge Distillation for Visual Question Answering

Stochastic Chebyshev Gradient Descent for Spectral Optimization

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Mining GOLD Samples for Conditional GANs

Consistency Regularization for Certified Robustness of Smoothed Classifiers

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Guiding Deep Molecular Optimization with Genetic Exploration

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Learning Bounds for Risk-sensitive Learning

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning

Time-Reversal Symmetric ODE Network

Learning from Failure: De-biasing Classifier from Biased Classifier

Scaling Neural Tangent Kernels via Sketching and Random Features

Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning

RoMA: Robust Model Adaptation for Offline Model-based Optimization

Meta-Learning Sparse Implicit Neural Representations

Object-aware Contrastive Learning for Debiased Scene Representation

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Meta-Learning with Self-Improving Momentum Target

RényiCL: Contrastive Representation Learning with Skew Rényi Divergence

Scalable Neural Video Representations with Learnable Positional Features

NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration

Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training

Guide Your Agent with Adaptive Multimodal Rewards

S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions

Multi-scale Diffusion Denoised Smoothing