Seongmin Kim

Yongjae Shin, Jongseong Chae, Seongmin Kim et al.

Action chunking emerged as a pivotal technique in imitation learning, enabling policies to predict cohesive action sequences rather than single actions. Recently, this approach has expanded to reinforcement learning (RL), enhancing behavioral consistency and reducing bootstrapping errors in value function estimation. However, existing methods rely on a fixed chunk length, creating a performance bottleneck as the optimal length varies across states and tasks. In this paper, we propose Adaptive Action CHunking (ACH), a novel offline-to-online RL algorithm that dynamically modulates chunk length during both training and inference. To find the optimal chunk length for a dynamically varying current state, we simultaneously estimate action-values for all candidate chunk lengths in a single forward pass, using a Transformer-based architecture. Our mechanism allows the agent to select the most effective chunk length adaptively based on the current state. Evaluated on 34 challenging tasks, ACH consistently outperforms fixed-length baselines, demonstrating superior generalization and learning efficiency in complex environments.

Seongmin Kim, Hyunjoon Cheon, Su-Hyeon Kim et al.

Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity-such as deeper nesting and frequent Unions-of real-world regexes. To overcome the resulting performance drop, we propose ReSyn, a synthesizer-agnostic divide-and-conquer framework that decomposes complex synthesis problems into manageable sub-problems. We also introduce Set2Regex, a parameter-efficient synthesizer capturing the permutation invariance of examples. Experimental results demonstrate that ReSyn significantly boosts accuracy across various synthesizers, and its combination with Set2Regex establishes a new state-of-the-art on challenging real-world benchmark.

Seongmin Kim, Daegyu Lee

Deploying a neuro-symbolic task planner on a new domain today requires significant manual effort: a domain expert must author relaxation and complementary rules, and hundreds of training problems must be solved to supervise a Graph Neural Network (GNN) object scorer. We propose LLM-Flax, a three-stage framework that eliminates all three sources of manual effort using a locally hosted LLM given only a PDDL domain file. Stage 1 automatically generates relaxation and complementary rules via structured prompting with format validation and self-correction. Stage 2 introduces LLM-guided failure recovery with a feasibility-gated budget policy that explicitly reserves API latency cost before each LLM call, preventing the downstream relaxation fallback from being starved. Stage 3 replaces the domain-trained GNN entirely with zero-shot LLM object importance scoring, requiring no training data. We evaluate all three stages on the MazeNamo benchmark across 10x10, 12x12, and 15x15 grids (8 benchmarks total). LLM-Flax achieves average SR 0.945 versus the manual baseline's 0.828 (+0.117), matching or outperforming manual rules on every one of the eight benchmarks. On 12x12 Expert, LLM-Flax attains SR 0.733 where the manual planner fails entirely (SR 0.000); on 15x15 Hard, it achieves SR 1.000 versus Manual's 0.900. Stage 3 demonstrates feasibility (SR 0.720 on 12x12 Hard with no training data) but faces a context-window bottleneck at scale, pointing to the primary open challenge for future work.

Seongmin Kim, Vincent R. Pascuzzi, Travis S. Humble et al.

Many real-world problems are naturally formulated as higher-order optimization (HUBO) tasks involving dense, multi-variable interactions, which are challenging to solve with classical methods. Quantum optimization offers a promising route, but hardware constraints and limitations to quadratic formulations have hampered their practicality. Here, we develop a distributed quantum optimization framework (DQOF) for dense, large-scale HUBO problems. DQOF assigns quantum circuits a central role in directly capturing higher-order interactions, while high-performance computing orchestrates large-scale parallelism and coordination. A clustering strategy enables wide quantum circuits without increasing depth, allowing efficient execution on near-term quantum hardware. We demonstrate high-quality solutions for HUBOs up to 500 variables within 170 seconds, significantly outperforming conventional approaches in solution quality and scalability. Applied to optical metamaterial design, DQOF efficiently discovers high-performance structures and shows that higher-order interactions are important for practical optimization problems. These results establish DQOF as a practical and scalable computational paradigm for large-scale scientific optimization.

Seongmin Kim, Kwanho Kim, Minseung Kim et al.

Although deep learning models owe their remarkable success to deep and complex architectures, this very complexity typically comes at the expense of real-time performance. To address this issue, a variety of model compression techniques have been proposed, among which knowledge distillation (KD) stands out for its strong empirical performance. The KD contains two concurrent processes: (i) matching the outputs of a large, pre-trained teacher network and a lightweight student network, and (ii) training the student to solve its designated downstream task. The associated loss functions are termed the distillation loss and the downsteam-task loss, respectively. Numerous prior studies report that KD is most effective when the influence of the distillation loss outweighs that of the downstream-task loss. The influence(or importance) is typically regulated by a balancing parameter. This paper provides a mathematical rationale showing that in a simple KD setting when the loss is decreasing, the balancing parameter should be dynamically adjusted

Kanghyun Jo, Jehwan Choi, Kwanho Kim et al.

Understanding and predicting human behavior has emerged as a core capability in various AI application domains such as autonomous driving, smart healthcare, surveillance systems, and social robotics. This paper defines the technical framework of Artificial Behavior Intelligence (ABI), which comprehensively analyzes and interprets human posture, facial expressions, emotions, behavioral sequences, and contextual cues. It details the essential components of ABI, including pose estimation, face and emotion recognition, sequential behavior analysis, and context-aware modeling. Furthermore, we highlight the transformative potential of recent advances in large-scale pretrained models, such as large language models (LLMs), vision foundation models, and multimodal integration models, in significantly improving the accuracy and interpretability of behavior recognition. Our research team has a strong interest in the ABI domain and is actively conducting research, particularly focusing on the development of intelligent lightweight models capable of efficiently inferring complex human behaviors. This paper identifies several technical challenges that must be addressed to deploy ABI in real-world applications including learning behavioral intelligence from limited data, quantifying uncertainty in complex behavior prediction, and optimizing model structures for low-power, real-time inference. To tackle these challenges, our team is exploring various optimization strategies including lightweight transformers, graph-based recognition architectures, energy-aware loss functions, and multimodal knowledge distillation, while validating their applicability in real-time environments.

Giseung Park, Woohyeon Byeon, Seongmin Kim et al.

In this paper, we consider multi-objective reinforcement learning, which arises in many real-world problems with multiple optimization goals. We approach the problem with a max-min framework focusing on fairness among the multiple goals and develop a relevant theory and a practical model-free algorithm under the max-min framework. The developed theory provides a theoretical advance in multi-objective reinforcement learning, and the proposed algorithm demonstrates a notable performance improvement over existing baseline methods.