Junsu Kim
14 papers · 2020–2026 · 7 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (40) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§
Keyword Pioneer
π
Grand Slam
π₯
Mega-Team Β· Squad
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Renaissance Researcher
(7)
ποΈ
Keyword Collector
(95)
Top co-authors
Research topics
Machine Learning
(11)
Deep Learning
(9)
Artificial Intelligence
(8)
Core AI
(7)
Learning Types Β· Machine Learning
(7)
Learning Types Β· Deep Learning
(5)
Computer Vision
(4)
Models
(4)
Reinforcement Learning
(3)
Application Areas
(3)
Architectures
(3)
Methods
(3)
Optimization & Theory
(3)
Analysis
(2)
Core Methods
(2)
Keywords
deep neural network
(2)
representation learning
(2)
self-supervised learning
(2)
theorem proving
(2)
molecular optimization
(1)
sample efficiency
(1)
reinforcement learning
(1)
imitation learning
(1)
catastrophic forgetting
(1)
robotic manipulation
(1)
scene understanding
(1)
object detection
(1)
symbolic reasoning
(1)
mathematical reasoning
(1)
knowledge distillation
(1)
online learning
(1)
benchmark evaluation
(1)
language modeling
(1)
test-time adaptation
(1)
continual learning
(1)
Papers
Learning Compact 3D Representations from Feed-Forward Novel View Synthesis
CVPR 2026
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
JMLR 2025
LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Wonβt Fail)
ICML 2025
Salient Frequency-aware Exemplar Compression for Resource-constrained Online Continual Learning
AAAI 2025
Test-Time Adaptation with Binary Feedback
ICML 2025
Towards Robust Mathematical Reasoning
EMNLP 2025
SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection
CVPR 2024
Visual Representation Learning with Stochastic Frame Prediction
ICML 2024
Imitating Graph-Based Planning with Goal-Conditioned Policies
ICLR 2023
Multi-View Masked World Models for Visual Robotic Manipulation
ICML 2023
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
ICML 2022
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning
NeurIPS 2021
Self-Improved Retrosynthetic Planning
ICML 2021
Guiding Deep Molecular Optimization with Genetic Exploration
NeurIPS 2020