Presented seven papers at Korea Software Congress 2023 π
Seven papers are accepted to KSC 2023. Check our papers (click).
κ°ννμ΅ / νλ μμν¬
- ARCLE: μΆμν λ° μΆλ‘ μ μν κ°ννμ΅ νκ²½ (μ°μλ°νλ Όλ¬Έμ μμ)
- μλ λͺ¨λΈμ μ΄μ©ν ARC λ¬Έμ μ μ¬μ μ§μ νκ°
- μλλͺ¨λΈμ ν΅ν ARCμ ν΅μ¬ μ§μ μΆμΆ
κΈ°κ³ νμ΅ / λ°©λ²λ‘
- κ·λ© νΈν₯ μ 곡μ μν μμ± μ΄ν μ νμ΅ (μ°μλ Όλ¬Έμ μμ)
- μΆμν λ° μΆλ‘ λ¬Έμ ν΄κ²°μ μν λμ‘°νμ΅
λ°μ΄ν°μ / λν μΈμ΄ λͺ¨λΈ
- λν μΈμ΄ λͺ¨λΈμ νμ©ν ν¨μ· μΆλ‘ λ¬Έμ μ λ°μ΄ν° μ¦κ° (μ°μλ°νλ Όλ¬Έμ μμ)
- κ±°λμΈμ΄λͺ¨λΈμ μΆλ‘ λ₯λ ₯ νκ°λ₯Ό μν MC-LARC λ°μ΄ν°μ
Reinforcement Learning / Framework
- ARCLE: Gymnasium Environment for Abstraction and Reasoning Corpus
- Evaluating Prior Knowledge of ARC Using World Models
- Extracting the Core Knowledge of ARC with the World Model
Machine Learning / Methodology
- Color Attention for Inductive Bias Provision
- Using Contrastive Learning for Abstraction and Reasoning Task
Dataset / Large Language Model
- Augmenting Few-Shot Demonstrations with Large Language Model
- MC-LARC Benchmark to Measure LLM Reasoning Capability