ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Su Jung Kim

Su Jung Kim

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:57 AM AMS

22

papers

243

total citations

papers (22)

Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention

MEVG : Multi-event Video Generation with Text-to-Video Models

Reasoning Models Better Express Their Confidence

NEURIPS 2025arXiv

Diffusion Model for Dense Matching

VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions

Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation

Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models

Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement

Spreading Out-of-Distribution Detection on Graphs

KLASS: KL-Guided Fast Inference in Masked Diffusion Models

NEURIPS 2025arXiv

Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers

Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection

ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos

Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability

NEURIPS 2025arXiv

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

NEURIPS 2025arXiv

FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning

Domain Reduction Strategy for Non-Line-of-Sight Imaging

When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class

Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks

NEURIPS 2025arXiv