arXiv subjects

Sejin Kim

Publications and source records attributed to Sejin Kim.

At least 19 recordsLinked to original sources

arXiv2026

Negative controls reveal volume-driven confounding in radiomics and imaging foundation model features

Radiomics and imaging foundation models promise non-invasive biomarkers of tumour biology, yet predictive signatures may reflect tumour volume or acquisition artifacts rather than meaningful image structure. We introduce READII-2-ROQC, an open-source framework that uses volume-preserving negative controls to assess whether radiomic and deep imaging features capture independent spatial signals. READII-2-ROQC generates voxel-perturbed images across tumour, background and whole-image regions using configurable randomization strategies, then compares feature behaviour and model performance between original and control images. Applied to three public cancer imaging cohorts, the framework processed 3,552 tumour volumes and extracted PyRadiomics and foundation-model features from original images and nine matched controls. Reproducing published survival and HPV-status signatures, we show that multiple models retain performance after spatial structure is destroyed, revealing volume-driven or contextual confounding, whereas others show perturbation-sensitive signal. READII-2-ROQC provides a scalable quality-control strategy for developing interpretable, biologically grounded imaging biomarkers and reproducible radiomics workflows.

cs.CV↗

arXiv2025

ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving

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 inspired extensive research on abstract reasoning, most existing approaches rely on static input-output supervision, which limits insight into how reasoning unfolds over time. ARCTraj addresses this gap by recording temporally ordered, object-level actions that capture how humans iteratively transform inputs into outputs, revealing intermediate reasoning steps that conventional datasets overlook. Collected via the O2ARC web interface, it contains around 10,000 trajectories annotated with task identifiers, timestamps, and success labels across 400 training tasks from the ARC-AGI-1 benchmark. It further defines a unified reasoning pipeline encompassing data collection, action abstraction, Markov decision process (MDP) formulation, and downstream learning, enabling integration with reinforcement learning, generative modeling, and sequence modeling methods such as PPO, World Models, GFlowNets, Diffusion agents, and Decision Transformers. Analyses of spatial selection, color attribution, and strategic convergence highlight the structure and diversity of human reasoning. Together, these contributions position ARCTraj as a structured and interpretable foundation for studying human-like reasoning, advancing explainability, alignment, and generalizable intelligence.

cs.AI↗

arXiv2025

Learning the Inverse Ryu--Takayanagi Formula with Transformers

We study the inverse problem of holographic entanglement entropy in AdS$_3$ using a data-driven generative model. Training data consist of randomly generated geometries and their holographic entanglement entropies using the Ryu--Takayanagi formula. After training, the Transformer reconstructs the blackening function within our metric ansatz from previously unseen inputs. The Transformer achieves accurate reconstructions on smooth black hole geometries and extrapolates to horizonless backgrounds. We describe the architecture and data generation process, and we quantify accuracy on both $f(z)$ and the reconstructed $S(\ell)$. Code and evaluation scripts are available at the provided repository.

hep-th↗

arXiv2025

Extracting Edge Modes: Reduction of 3D and 2D Gravities

We investigate the boundary reduction of 3D Einstein gravity and JT gravity into their respective edge mode theories - namely, the Liouville and Alekseev-Shatashvili, and Schwarzian models. By examining the roles of boundary conditions, canonical transformations, and differing formulations - metric versus Chern-Simons - we clarify how physical degrees of freedom become localized at the boundary and resolve several long-standing ambiguities in the reduction procedure.

hep-th↗

arXiv2025

TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design

Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates tasks with high learning potential, while a student learns a robust policy from this evolving curriculum. Existing UED methods typically measure learning potential via regret, the gap between optimal and current performance, approximated solely by value-function loss. Building on these approaches, we introduce the transition-prediction error as an additional term in our regret approximation. To capture how training on one task affects performance on others, we further propose a lightweight metric called Co-Learnability. By combining these two measures, we present Transition-aware Regret Approximation with Co-learnability for Environment Design (TRACED). Empirical evaluations show that TRACED produces curricula that improve zero-shot generalization over strong baselines across multiple benchmarks. Ablation studies confirm that the transition-prediction error drives rapid complexity ramp-up and that Co-Learnability delivers additional gains when paired with the transition-prediction error. These results demonstrate how refined regret approximation and explicit modeling of task relationships can be leveraged for sample-efficient curriculum design in UED. Project Page: https://geonwoo.me/traced/

cs.LG↗

arXiv2024

Data-driven development of cycle prediction models for lithium metal batteries using multi modal mining

Recent advances in data-driven research have shown great potential in understanding the intricate relationships between materials and their performances. Herein, we introduce a novel multi modal data-driven approach employing an Automatic Battery data Collector (ABC) that integrates a large language model (LLM) with an automatic graph mining tool, Material Graph Digitizer (MatGD). This platform enables state-of-the-art accurate extraction of battery material data and cyclability performance metrics from diverse textual and graphical data sources. From the database derived through the ABC platform, we developed machine learning models that can accurately predict the capacity and stability of lithium metal batteries, which is the first-ever model developed to achieve such predictions. Our models were also experimentally validated, confirming practical applicability and reliability of our data-driven approach.

cs.LG↗

arXiv2024

Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task

Effective long-term strategies enable AI systems to navigate complex environments by making sequential decisions over extended horizons. Similarly, reinforcement learning (RL) agents optimize decisions across sequences to maximize rewards, even without immediate feedback. To verify that Latent Diffusion-Constrained Q-learning (LDCQ), a prominent diffusion-based offline RL method, demonstrates strong reasoning abilities in multi-step decision-making, we aimed to evaluate its performance on the Abstraction and Reasoning Corpus (ARC). However, applying offline RL methodologies to enhance strategic reasoning in AI for solving tasks in ARC is challenging due to the lack of sufficient experience data in the ARC training set. To address this limitation, we introduce an augmented offline RL dataset for ARC, called Synthesized Offline Learning Data for Abstraction and Reasoning (SOLAR), along with the SOLAR-Generator, which generates diverse trajectory data based on predefined rules. SOLAR enables the application of offline RL methods by offering sufficient experience data. We synthesized SOLAR for a simple task and used it to train an agent with the LDCQ method. Our experiments demonstrate the effectiveness of the offline RL approach on a simple ARC task, showing the agent's ability to make multi-step sequential decisions and correctly identify answer states. These results highlight the potential of the offline RL approach to enhance AI's strategic reasoning capabilities.

cs.AI↗

arXiv2024

DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation

We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We address two key challenges in offline RL: out-of-distribution samples and long-horizon problems. We leverage diffusion models to learn state-action sequence distributions and incorporate value functions for more balanced and adaptive decision-making. DIAR introduces an Adaptive Revaluation mechanism that dynamically adjusts decision lengths by comparing current and future state values, enabling flexible long-term decision-making. Furthermore, we address Q-value overestimation by combining Q-network learning with a value function guided by a diffusion model. The diffusion model generates diverse latent trajectories, enhancing policy robustness and generalization. As demonstrated in tasks like Maze2D, AntMaze, and Kitchen, DIAR consistently outperforms state-of-the-art algorithms in long-horizon, sparse-reward environments.

cs.LG↗

arXiv2024

System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI

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 weaknesses on ARC-AGI tasks, revealing gaps in compositional generalization and novel-rule adaptation, and argue that closing these gaps requires overhauling the reasoning pipeline and its evaluation. We propose three research axes: (1) Symbolic representation pipeline for compositional generality, (2) Interactive feedback-driven reasoning loop for adaptivity, and (3) Test-time task augmentation balancing both qualities. Finally, we demonstrate how ARC-AGI's evaluation suite can be adapted to track progress in symbolic generality, feedback-driven adaptivity, and task-level robustness, thereby guiding future work on robust human--AI alignment.

cs.AI↗

arXiv2024

Phase Diagram from Nonlinear Interaction between Superconducting Order and Density: Toward Data-Based Holographic Superconductor

We address an inverse problem in modeling holographic superconductors. We focus our research on the critical temperature behavior depicted by experiments. We use a physics-informed neural network method to find a mass function $M(F^2)$, which is necessary to understand phase transition behavior. This mass function describes a nonlinear interaction between superconducting order and charge carrier density. We introduce positional embedding layers to improve the learning process in our algorithm, and the Adam optimization is used to predict the critical temperature data via holographic calculation with appropriate accuracy. Consideration of the positional embedding layers is motivated by the transformer model of natural-language processing in the artificial intelligence (AI) field. We obtain holographic models that reproduce borderlines of the normal and superconducting phases provided by actual data. Our work is the first holographic attempt to match phase transition data quantitatively obtained from experiments. Also, the present work offers a new methodology for data-based holographic models.

hep-th↗

arXiv2024

Addressing and Visualizing Misalignments in Human Task-Solving Trajectories

Understanding misalignments in human task-solving trajectories is crucial for enhancing AI models trained to closely mimic human reasoning. This study categorizes such misalignments into three types: (1) lack of functions to express intent, (2) inefficient action sequences, and (3) incorrect intentions that cannot solve the task. To address these issues, we first formalize and define these three misalignment types in a unified framework. We then propose a heuristic algorithm to detect misalignments in ARCTraj trajectories and analyze their impact hierarchically and quantitatively. We also present an intention estimation method based on our formalism that infers missing alignment between user actions and intentions. Through trajectory alignment, we experimentally demonstrate that AI models trained on human task-solving trajectories improve performance in mimicking human reasoning. Based on hierarchical analysis and experiments, we highlight the importance of trajectory-intention alignment and demonstrate the effectiveness of intention-aligned training.

cs.AI↗

arXiv2024

Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL

This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks.

cs.AI↗

arXiv2024

ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning

This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based on these insights, we propose several research directions and motivations for using ARCLE, including MAML, GFlowNets, and World Models.

cs.AI↗

arXiv2024

Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus

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 process comprehensively. We introduce a novel approach using the Abstraction and Reasoning Corpus (ARC) benchmark to evaluate the inference and contextual understanding abilities of LLMs in a process-centric manner, focusing on three key components from the Language of Thought Hypothesis (LoTH): Logical Coherence, Compositionality, and Productivity. Our carefully designed experiments reveal that while LLMs demonstrate some inference capabilities, they still significantly lag behind human-level reasoning in these three aspects. The main contribution of this paper lies in introducing the LoTH perspective, which provides a method for evaluating the reasoning process that conventional results-oriented approaches fail to capture, thereby offering new insights into the development of human-level reasoning in artificial intelligence systems.

cs.CL↗

arXiv2023

Construction of Superconducting Dome and Emergence of Quantum Critical Region in Holography

In this work, we investigate an extended model of holographic superconductor by a non-linear electrodynamic interaction coupled to a complex scalar field. This non-linear interaction term can make a quantum phase transition at zero temperature with finite charge carrier density. By solving full equations of motion, we can construct various shapes of the superconducting phase in the phase diagram. With a specific choice of interaction coefficients, we can construct a phase diagram with a superconducting dome. Also, we find a new geometric solution inside the superconducting dome, which turns out to be a Lifshitz-type geometry. This geometry is characterized by a dynamical critical exponent, which plays a crucial role near the quantum critical point. We refer to this region in the phase diagram as a `quantum critical region.'

hep-th↗

arXiv2023

Holography Transformer

We have constructed a generative artificial intelligence model to predict dual gravity solutions when provided with the input of holographic entanglement entropy. The model utilized in our study is based on the transformer algorithm, widely used for various natural language tasks including text generation, summarization, and translation. This algorithm possesses the ability to understand the meanings of input and output sequences by utilizing multi-head attention layers. In the training procedure, we generated pairs of examples consisting of holographic entanglement entropy data and their corresponding metric solutions. Once the model has completed the training process, it demonstrates the ability to generate predictions regarding a dual geometry that corresponds to the given holographic entanglement entropy. Subsequently, we proceed to validate the dual geometry to confirm its correspondence with the holographic entanglement entropy data.

hep-th↗

arXiv2023

End of the World Perspective to BCFT

In this work, we study the end-of-the-world (EOW) branes anchored to the boundaries of BCFT${}_2$ dual to the BTZ black hole. First, we explore the thermodynamics of the boundary system consisting of the conformal boundary and two EOW branes. This thermodynamics is extended by the tension appearing as the effective cosmological constant of JT black holes on the EOW branes. The tension contribution is identified with the shadow entropy equivalent to the boundary entropy of the BCFT${}_2$. The thermodynamics of the JT black holes and the bulk of BCFT${}_2$ can be combined into a novel grafted thermodynamics based on the first law. Second, we focus on the observer's view of the EOW branes by lowering the temperature. We show that the EOW branes generate a scale called ``reefs" inside the horizon. This scale also appears in the grafted thermodynamics. At high temperatures, observers on the EOW branes see their respective event horizons. The reef starts to grow relatively to the horizon size at the temperature, $T_{grow}$. As the temperature cools down the reef area fills the entire interior of the JT black holes at the temperature $T_{out}$. Then, the observers recognize their horizons disappear and see the large density of the energy flux. At this temperature, the two JT regions become causally connected. This connected spacetime has two asymptotic $AdS_2$ boundaries with a conformal matter. Also, we comment on the grafted thermodynamics to higher dimensions in Appendix B.

hep-th↗

arXiv2023

Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer

In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach. We employ the Decision Transformer in an imitation learning paradigm to model human problem-solving, and introduce an object detection algorithm, the Push and Pull clustering method. This dual strategy enhances AI's ARC problem-solving skills and provides insights for AGI progression. Yet, our work reveals the need for advanced data collection tools, robust training datasets, and refined model structures. This study highlights potential improvements for Decision Transformers and propels future AGI research.

cs.AI↗