2026 Course 2. LLM(VLM) Reasoning
Scaling Laws for Neural Language Models, Emergent Abilities of LLMs / YoungMin Kim
Chain-of-Thought Prompting Elicits Reasoning / HyunJi Jeon
Self-Consistency Improves CoT Reasoning / JiHun Kim
Least-to-Most Prompting Enables Complex Reasoning / JunSeok Lee
Tree of Thoughts: Deliberate Problem Solving / TaeHoon Lee
Training Verifiers to Solve Math Word Problems, Let's Verify Step by Step / HeeSu Jo
LMs Don't Always Say What They Think (Unfaithful CoT), Reasoning Models Don't Always Say What They Think / Gunhee Lee
Scaling LLM Test-Time Compute Optimally / HeeSu Jo
DeepSeek-R1: Incentivizing Reasoning via RL, s1: Simple Test-Time Scaling / JiHun Kim
GSM-Symbolic: Limitations of Math Reasoning, The Illusion of Thinking / TaeHoon Lee
ReAct: Synergizing Reasoning and Acting, Toolformer: LMs Can Teach Themselves to Use Tools / HyunJi Jeon
Reflexion: Verbal Reinforcement / YoungMin Kim
τ-bench: Tool-Agent-User Interaction, AMA-Bench: Long-Horizon Memory for Agents / JunSeok Lee
Agentic Memory (AgeMem): Unified LTM/STM, Memory for Autonomous LLM Agents / Gunhee Lee
2026 Course 1. GNN and Mamba
그래프의 기본 성질과 GCN; Graph Convolution Network / TaeHoon Lee
GraphSAGE; Inductive Representation Learning on Large Graphs / MyeongSeop Kim
GAT; Graph Attention Network / JiHun Kim
GIN; How Powerful are Graph Neural Networks? & WL Test / ByungWoo Kim
GNN Explainer; Generating Explanations for Graph Neural Networks / JeongA Seol
Application1. Spatial Transcriptomics / MyeongSeop Kim
Application 2; / ByungWoo Kim
Application 3; / JeongA Seol
Application 4; / WooKyung Kim
State Space Model / MyeongSeop Kim
Structered State Space for Sequence Modeling / JeongA Seol
Mamba 1: Selective State Space / TaeHoon Lee
Mamba 2: Hardware-aware Algorithm & Mamba Architecture / ByungWoo Kim
Mamba for signal & Time Series
Vision Mamba; Efficient Visual Representation Learning with Bidirectional State Space Model
Next Coming
2026 Course 3. Generative Models
Course 4. Reinforcement Learning