7 papers
TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
Geonwoo Cho, Jaegyun Im, Jihwan Lee +3
Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolut…
ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving
Sejin Kim, Hayan Choi, Seokki Lee +1
We present ARCTraj, a dataset and methodological framework for modeling human reasoning through complex visual tasks in the Abstraction and Reasoning Corpus (ARC). While ARC has in…
System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI
Sejin Kim, Sundong Kim
Despite their broad applicability, transformer-based models still fall short in System~2 reasoning, lacking the generality and adaptivity needed for human--AI alignment. We examine…
Addressing and Visualizing Misalignments in Human Task-Solving Trajectories
Sejin Kim, Hosung Lee, Sundong Kim
Understanding misalignments in human task-solving trajectories is crucial for enhancing AI models trained to closely mimic human reasoning. This study categorizes such misalignment…
Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus
Seungpil Lee, Woochang Sim, Donghyeon Shin +6
The existing methods for evaluating the inference abilities of Large Language Models (LLMs) have been predominantly results-centric, making it challenging to assess the inference p…
DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation
Jaehyun Park, Yunho Kim, Sejin Kim +2
We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We a…