Sungduk Yu
7 papers · 2023–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
👥
Mega-Team · Legion
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(5)
Machine Learning
(5)
Core AI
(5)
Deep Learning
(3)
Optimization & Theory
(3)
Application Areas
(2)
Models
(2)
Data Science & Analytics
(1)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Architectures
(1)
Core Methods
(1)
Learning Types
(1)
Methods
(1)
Reasoning
(1)
Keywords
high-resolution simulation
(2)
language modeling
(1)
kv cache compression
(1)
time series
(1)
mixture of expert
(1)
vision-language model
(1)
world model
(1)
climate prediction
(1)
subseasonal forecasting
(1)
physics-informed model
(1)
ensemble forecast
(1)
weather emulator
(1)
boundary condition
(1)
large vision-language model
(1)
multimodal learning
(1)
expert routing
(1)
climate simulation
(1)
weight compression
(1)
confidence score
(1)
attention mechanism
(1)
Papers
A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
ICML 2025
ClimSim-Online: A Large Multi-Scale Dataset and Framework for Hybrid Physics-ML Climate Emulation
JMLR 2025
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression
NAACL 2025
Probing Semantic Routing in Large Mixture-of-Expert Models
EMNLP 2025
ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
NeurIPS 2024
Why do LLaVA Vision-Language Models Reply to Images in English?
EMNLP 2024
ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
NeurIPS 2023