Sanghyeok Lee
13 papers · 2021–2026 · 5 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (23)
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
ποΈ
Keyword Collector
(62)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Deep Learning
(8)
Machine Learning
(8)
Artificial Intelligence
(7)
Application Areas
(7)
Core AI Β· Artificial Intelligence
(7)
Architectures
(6)
Computer Vision
(5)
Optimization & Theory
(3)
Techniques
(3)
Analysis
(2)
Core AI Β· Computer Vision
(2)
Learning Paradigms
(2)
Processing
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Keywords
vision-language model
(5)
efficient computing
(3)
image classification
(2)
point cloud
(2)
data augmentation
(2)
attention mechanism
(2)
part segmentation
(2)
parameter efficiency
(2)
shape classification
(2)
3d vision
(2)
token pruning
(2)
transfer learning
(1)
neural network optimization
(1)
neural architecture
(1)
model adaptation
(1)
domain generalization
(1)
semantic segmentation
(1)
speed-accuracy tradeoff
(1)
few-shot learning
(1)
scene segmentation
(1)
Papers
DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
CVPR 2026
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
CVPR 2026
TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing
AAAI 2026
Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
AAAI 2026
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
CVPR 2025
Representation Shift: Unifying Token Compression with FlashAttention
ICCV 2025
Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
EMNLP 2025
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
CVPR 2024
vid-TLDR: Training Free Token Merging for Light-weight Video Transformer
CVPR 2024
Read-only Prompt Optimization for Vision-Language Few-shot Learning
ICCV 2023
Self-Positioning Point-Based Transformer for Point Cloud Understanding
CVPR 2023
SageMix: Saliency-Guided Mixup for Point Clouds
NeurIPS 2022
Point Cloud Augmentation With Weighted Local Transformations
ICCV 2021