Dongjun Kim
19 papers · 2020–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (41) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π₯
Mega-Team Β· Squad
π
Grand Slam
π§¬
Topic Evolution
π
Triple Crown
π¬
Deep Specialist
(10)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(84)
Top co-authors
Research topics
Deep Learning
(14)
Models
(11)
Machine Learning
(9)
Artificial Intelligence
(7)
Computer Vision
(6)
Core AI
(6)
Generation
(6)
Optimization & Theory
(5)
Application Areas
(4)
Learning Types Β· Deep Learning
(4)
Natural Language Processing
(3)
Architectures
(3)
Resources & Methods
(3)
Learning Types Β· Machine Learning
(2)
Applications
(1)
Keywords
diffusion model
(9)
image generation
(5)
large language model
(4)
generative model
(3)
knowledge distillation
(3)
attention mechanism
(2)
score-based model
(2)
score matching
(2)
one-step generation
(2)
latent diffusion
(2)
domain adaptation
(1)
toxicity detection
(1)
bias detection
(1)
image synthesis
(1)
named entity recognition
(1)
online learning
(1)
mean field theory
(1)
model interpretability
(1)
knowledge editing
(1)
dense retrieval
(1)
Papers
LangSAE Editing: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
ACL 2026
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation
ACL 2026
Selective Span-Level Unlearning for Large Language Models
ACL 2026
Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
EMNLP 2025
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
ACL 2025
HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning
ICLR 2025
KoLEG: On-the-Fly Korean Legal Knowledge Editing with Continuous Retrieval
EMNLP 2025
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation
ICLR 2025
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
ICLR 2024
Exploring Inherent Biases in LLMs within Korean Social Context: A Comparative Analysis of ChatGPT and GPT-4
NAACL 2024
Manifold Preserving Guided Diffusion
ICLR 2024
Mean-field Chaos Diffusion Models
ICML 2024
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
NeurIPS 2024
Training Unbiased Diffusion Models From Biased Dataset
ICLR 2024
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
ICML 2023
Maximum Likelihood Training of Implicit Nonlinear Diffusion Model
NeurIPS 2022
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
ICML 2022
Implicit Kernel Attention
AAAI 2021
Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence
CVPR 2020