arXiv subjects

Sumin Park

Publications and source records attributed to Sumin Park.

14 recordsLinked to original sources

arXiv2026

Q-Delta: Beyond Key-Value Associative State Evolution

Linear attention reformulates sequence modeling as recurrent state evolution, enabling efficient linear-time inference. Under the key-value associative paradigm, existing approaches restrict the role of the query to the readout operation, decoupling it from state evolution. We show that query-conditioned state readout induces a structured value prediction over accumulated memory that complements key-based retrieval. Based on this insight, we propose Q-Delta, a query-aware delta rule that integrates mixed key-query prediction errors into state evolution, enabling jointly corrective dynamics while preserving delta-rule efficiency. We establish stability guarantees for the resulting dynamics and derive a hardware-efficient chunkwise-parallel formulation with a custom Triton implementation. Empirical results demonstrate stable optimization, competitive throughput, and consistent improvements over strong baselines on language modeling and long-context retrieval tasks.

cs.AI↗

arXiv2026

STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning

Mixture-of-Experts (MoE) scales model capacity efficiently by selectively routing inputs to a specialized subset of experts. However, input-expert specialization, the core motivation of MoE, critically depends on whether the router is actually aware of input structure. In practice, MoE routing is typically implemented as a shallow linear projection with limited awareness of input representation, which often leads to unstable routing. We propose STAR, a Structure Aware Routing that rethinks MoE routing as a subspace learning problem by augmenting standard learnable routing with an evolving principal subspace that tracks dominant input structure via Generalized Hebbian Algorithm (GHA). By aligning routing decisions directly with input structure, STAR enables stable expert specialization. We evaluate STAR on controlled synthetic setup and large-scale language and vision tasks, where it consistently improves routing quality and downstream performance over strong MoE baselines. Moreover, optional test-time subspace updates further enhance routing robustness and generalization under input distribution shifts.

cs.AI↗

arXiv2026

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1\% of the data, RoboAlign achieves performance improvements of 17.5\%, 18.9\%, and 106.6\% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.

cs.AI↗

arXiv2026

FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy

Accurate focus quality assessment (FQA) in fluorescence microscopy is challenging due to stain-dependent optical variations that induce heterogeneous focus behavior across images. Existing methods, however, treat focus quality as a stain-agnostic problem, assuming a shared global ordering. We formulate stain-aware FQA for fluorescence microscopy, showing that focus-rank relationships vary substantially across stains due to stain-dependent imaging characteristics and invalidate this assumption. To support this formulation, we introduce FluoMix, the first dataset for stain-aware FQA spanning multiple tissues, fluorescent stains, and focus levels. We further propose FluoCLIP, a two-stage vision-language framework that grounds stain semantics and enables stain-conditioned ordinal reasoning for focus prediction, effectively decoupling stain representation from ordinal structure. By explicitly modeling stain-dependent focus behavior, FluoCLIP consistently outperforms both conventional FQA methods and recent vision-language baselines, demonstrating strong generalization across diverse fluorescence microscopy conditions. Code and dataset are publicly available at https://fluoclip.github.io/.

eess.IV↗

arXiv2025

How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts

Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frameworks either heavily rely on hyperparameter tuning or overlook the importance of diversifying semantic roles across experts when adapting the expert pool size. We propose Mixture-of-Experts for Adaptive Semantic Specialization (MASS), a semanticaware MoE framework for adaptive expert expansion and dynamic routing. MASS introduces two key advancements: (i) a gradient-based semantic drift detector that prompts targeted expert expansion when the existing expert pool lacks capacity to capture the full semantic diversity of the data, and (ii) an integration of adaptive routing strategy that dynamically adjusts expert usage based on token-level routing confidence mass. We first demonstrate that MASS reliably converges to the point of optimal balance between cost-performance trade-off with notably improved sematic specialization in a highly controlled synthetic setup. Further empirical results on real-world datasets across language and vision domains show that MASS consistently outperforms a range of strong MoE baselines, demonstrating its domain robustness and enhanced expert specialization.

cs.LG↗

arXiv2025

Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs

Graph Neural Networks (GNNs) have emerged as powerful tools for learning on graph-structured data, but often struggle to balance local and global information. While graph Transformers aim to address this by enabling long-range interactions, they often overlook the inherent locality and efficiency of Message Passing Neural Networks (MPNNs). We propose a new concept called fractal nodes, inspired by the fractal structure observed in real-world networks. Our approach is based on the intuition that graph partitioning naturally induces fractal structure, where subgraphs often reflect the connectivity patterns of the full graph. Fractal nodes are designed to coexist with the original nodes and adaptively aggregate subgraph-level feature representations, thereby enforcing feature similarity within each subgraph. We show that fractal nodes alleviate the over-squashing problem by providing direct shortcut connections that enable long-range propagation of subgraph-level representations. Experiment results show that our method improves the expressive power of MPNNs and achieves comparable or better performance to graph Transformers while maintaining the computational efficiency of MPNN by improving the long-range dependencies of MPNN.

cs.LG↗

arXiv2025

Phase-Space Topology in a Single-Atom Synthetic Dimension

We investigate topological features in the synthetic Fock-state lattice (FSL) of a single-atom system described by the quantum Rabi model. By diagonalizing the Hamiltonian, we identify a zero-energy defect state localized at a domain wall of the FSL, whose spin polarization is topologically protected. To address the challenge of applying band topology to the FSL, we introduce a physically motivated and directly measurable topological invariant based on phase-space geometry-the phase-space winding number. We show that the Zak phase, computed using a phase-space parameter, is related to the invariant. This quantized geometric phase reflects the spin polarization of the defect state, demonstrating a bulk-boundary correspondence. The resulting phase-space topology reveals the emergence of single-atom dressed states with contrasting properties-topologically protected spin states and driving-tunable bosonic states. Our results establish phase-space topology as a novel framework for exploring topological physics in single-atom synthetic dimensions, uncovering quantum-unique topological protection distinct from classical analogs.

quant-ph↗

arXiv2025

Adaptive Task Vectors for Large Language Models

In-Context Learning (ICL) enables Large Language Models (LLMs) to perform tasks without parameter updates by conditioning on a few demonstrations provided in the prompt. Despite its success, ICL suffers from several limitations, including sensitivity to demonstration order, context length constraints, and computational inefficiency. To address these challenges, task vector-based approaches compress task information into a single vector. However, these methods typically construct task vectors from fixed sets of demonstrations and reuse them across input queries, without conditioning on the specific input. This limitation can lead models to struggle with effective adaptation when the input query is not well aligned with the underlying demonstrations, consequently degrading their generalization performance on unseen tasks. To overcome this limitation, we propose Adaptive Task Vectors (ATV), a simple and effective framework that dynamically generates task vectors conditioned on each input query. ATV employs a small language model to generate task vectors, which are then transformed to match the target LLM's architecture and applied to guide its output generation. In contrast to ICL and previous vector-based approaches, which rely on fixed demonstration sets and their corresponding vectors, ATV dynamically generates task vectors tailored to each specific input query and task. Consequently, ATV demonstrates strong performance and generalization capabilities, even for unseen tasks. Furthermore, we provide a theoretical analysis indicating that ATV is expressively equivalent to LoRA under equal rank budgets and more expressive than Prefix-Tuning, thereby offering formal support for its representational advantage.

cs.LG↗

arXiv2025

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using Supervised Fine-Tuning (SFT). However, SFT datasets are often heuristically constructed and not explicitly optimized for improving robot control. Furthermore, SFT often leads to issues such as catastrophic forgetting and reduced generalization performance. To address these limitations, we introduce Robot-R1, a novel framework that leverages reinforcement learning to enhance embodied reasoning specifically for robot control. Robot-R1 learns to predict the next keypoint state required for task completion, conditioned on the current scene image and environment metadata derived from expert demonstrations. Inspired by the DeepSeek-R1 learning approach, Robot-R1 samples reasoning-based responses and reinforces those that lead to more accurate predictions. To rigorously evaluate Robot-R1, we also introduce a new benchmark that demands the diverse embodied reasoning capabilities for the task. Our experiments show that models trained with Robot-R1 outperform SFT methods on embodied reasoning tasks. Despite having only 7B parameters, Robot-R1 even surpasses GPT-4o on reasoning tasks related to low-level action control, such as spatial and movement reasoning.

cs.RO↗

arXiv2025

Efficient Quantum Frequency Conversion of Ultra-Violet Single Photons from a Trapped Ytterbium Ion

Ion trap system is a leading candidate for quantum network privileged by its long coherence time, high-fidelity gate operations, and the ion-photon entanglement that generates an ideal pair of a stationary memory qubit and a flying communication qubit. Rapid developments in nonlinear quantum frequency conversion techniques have enhanced the potential for constructing a trapped ion quantum network via optical fiber connections. The generation of long-distance entanglement has been demonstrated with ions such as Ca$^{+}$ and Ba$^{+}$, which emit photons in visible or near-infrared range naturally. On the other hand, as the qubit-native photons reside in ultra-violet (UV) spectrum, the Yb$^{+}$ ion has not been considered as a strong competitor for telecommunication qubits despite extensive research on it. Here, we demonstrate an efficient difference-frequency conversion of UV photons, emitted from a trapped Yb$^{+}$ ion, into a visible range. We provide experimental evidence that confirms the converted photons are radiated from the Yb$^{+}$ ion. Our results provide a crucial step toward realizing a long-distance trapped ion quantum network based on Yb$^{+}$ ions through quantum frequency conversion.

quant-ph↗

arXiv2024

Proleptic Temporal Ensemble for Improving the Speed of Robot Tasks Generated by Imitation Learning

Imitation learning, which enables robots to learn behaviors from demonstrations by human, has emerged as a promising solution for generating robot motions in such environments. The imitation learning-based robot motion generation method, however, has the drawback of depending on the demonstrator's task execution speed. This paper presents a novel temporal ensemble approach applied to imitation learning algorithms, allowing for execution of future actions. The proposed method leverages existing demonstration data and pre-trained policies, offering the advantages of requiring no additional computation and being easy to implement. The algorithms performance was validated through real-world experiments involving robotic block color sorting, demonstrating up to 3x increase in task execution speed while maintaining a high success rate compared to the action chunking with transformer method. This study highlights the potential for significantly improving the performance of imitation learning-based policies, which were previously limited by the demonstrator's speed. It is expected to contribute substantially to future advancements in autonomous object manipulation technologies aimed at enhancing productivity.

cs.RO↗

arXiv2024

LoraMap: Harnessing the Power of LoRA Connections

Fact-checking techniques can mitigate hallucinations in Large Language Models (LLMs), a prominent issue in specialized domains. As parameter-efficient techniques such as Low-Rank Adaptation (LoRA) can overcome substantial computational overhead, some studies have explored the integration of multiple LoRAs. While previous studies focus on parallel integration, this paper investigates methods to establish connections among multiple LoRAs. We create three reasoning datasets tailored to fact-checking and fine-tune individual LoRAs, allowing them to view and reason from diverse perspectives. Then, we explore strategies for allocating these reasoning LoRAs and introduce LoraMap, an approach to map connections between them. The results of the fact-checking task demonstrate that the performance of LoraMap is superior to LoraHub, an existing method for integrating LoRAs. LoraMap also outperforms with significantly fewer trainable parameters than LoraConcat, which concatenates LoRAs and further fine-tunes them.

cs.CL↗

arXiv2024

PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts that aim at optimizing the spatial or spectral properties of graphs to promote the signal propagation. However, such approaches inevitably deteriorate the original graph topology, which may lead to a distortion of information flow. To address this, we introduce an expanded width-aware (PANDA) message passing, a new message passing paradigm where nodes with high centrality, a potential source of over-squashing, are selectively expanded in width to encapsulate the growing influx of signals from distant nodes. Experimental results show that our method outperforms existing rewiring methods, suggesting that selectively expanding the hidden state of nodes can be a compelling alternative to graph rewiring for addressing the over-squashing.

cs.LG↗

arXiv2024

Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition

Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), which we are now presenting to the public. With the KBMC dataset, we noticed an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. This research underscores the significant benefits and importance of using specialized tools and datasets, like ChatGPT, to enhance language processing in specialized fields such as healthcare.

cs.CL↗