JaeYoon Kim

Jaeyoon Kim, Yoonki Cho, Sung-Eui Yoon

Visual Place Recognition (VPR) has advanced significantly with high-capacity foundation models like DINOv2, achieving remarkable performance. Nonetheless, their substantial computational cost makes deployment on resource-constrained devices impractical. In this paper, we introduce an efficient asymmetric VPR framework that incorporates a high-capacity gallery model for offline feature extraction with a lightweight query network for online processing. A key challenge in this setting is ensuring compatibility between these heterogeneous networks, which conventional approaches address through computationally expensive k-NN-based compatible training. To overcome this, we propose a geographical memory bank that structures gallery features using geolocation metadata inherent in VPR databases, eliminating the need for exhaustive k-NN computations. Additionally, we introduce an implicit embedding augmentation technique that enhances the query network to model feature variations despite its limited capacity. Extensive experiments demonstrate that our method not only significantly reduces computational costs but also outperforms existing asymmetric retrieval techniques, establishing a new aspect for VPR in resource-limited environments. The code is available at https://github.com/jaeyoon1603/AsymVPR

Yoonki Cho, Jaeyoon Kim, Woo Jae Kim et al.

Domain generalizable person re-identification (DG re-ID) aims to learn discriminative representations that are robust to distributional shifts. While data augmentation is a straightforward solution to improve generalization, certain augmentations exhibit a polarized effect in this task, enhancing in-distribution performance while deteriorating out-of-distribution performance. In this paper, we investigate this phenomenon and reveal that it leads to sparse representation spaces with reduced uniformity. To address this issue, we propose a novel framework, Balancing Alignment and Uniformity (BAU), which effectively mitigates this effect by maintaining a balance between alignment and uniformity. Specifically, BAU incorporates alignment and uniformity losses applied to both original and augmented images and integrates a weighting strategy to assess the reliability of augmented samples, further improving the alignment loss. Additionally, we introduce a domain-specific uniformity loss that promotes uniformity within each source domain, thereby enhancing the learning of domain-invariant features. Extensive experimental results demonstrate that BAU effectively exploits the advantages of data augmentation, which previous studies could not fully utilize, and achieves state-of-the-art performance without requiring complex training procedures. The code is available at \url{https://github.com/yoonkicho/BAU}.

Dongjun Jang, Sangah Lee, Sungjoo Byun et al.

This paper presents the DaG LLM (David and Goliath Large Language Model), a language model specialized for Korean and fine-tuned through Instruction Tuning across 41 tasks within 13 distinct categories.

Kyu Beom Han, Jaeyoon Kim, Woo Jae Kim et al.

Inverse rendering with Gaussian Splatting has advanced rapidly, but accurately disentangling material properties from complex global illumination effects, particularly indirect illumination, remains a major challenge. Existing methods often query indirect radiance from Gaussian primitives pre-trained for novel-view synthesis. However, these pre-trained Gaussian primitives are supervised only towards limited training viewpoints, thus lack supervision for modeling indirect radiances from unobserved views. To address this issue, we introduce radiometric consistency, a novel physically-based constraint that provides supervision towards unobserved views by minimizing the residual between each Gaussian primitive's learned radiance and its physically-based rendered counterpart. Minimizing the residual for unobserved views establishes a self-correcting feedback loop that provides supervision from both physically-based rendering and novel-view synthesis, enabling accurate modeling of inter-reflection. We then propose Radiometrically Consistent Gaussian Surfels (RadioGS), an inverse rendering framework built upon our principle by efficiently integrating radiometric consistency by utilizing Gaussian surfels and 2D Gaussian ray tracing. We further propose a finetuning-based relighting strategy that adapts Gaussian surfel radiances to new illuminations within minutes, achieving low rendering cost (<10ms). Extensive experiments on existing inverse rendering benchmarks show that RadioGS outperforms existing Gaussian-based methods in inverse rendering, while retaining the computational efficiency.

Hyopil Shin, Sangah Lee, Dongjun Jang et al.

We introduce KoBALT (Korean Benchmark for Advanced Linguistic Tasks), a comprehensive linguistically-motivated benchmark comprising 700 multiple-choice questions spanning 24 phenomena across five linguistic domains: syntax, semantics, pragmatics, phonetics/phonology, and morphology. KoBALT is designed to advance the evaluation of large language models (LLMs) in Korean, a morphologically rich language, by addressing the limitations of conventional benchmarks that often lack linguistic depth and typological grounding. It introduces a suite of expert-curated, linguistically motivated questions with minimal n-gram overlap with standard Korean corpora, substantially mitigating the risk of data contamination and allowing a more robust assessment of true language understanding. Our evaluation of 20 contemporary LLMs reveals significant performance disparities, with the highest-performing model achieving 61\% general accuracy but showing substantial variation across linguistic domains - from stronger performance in semantics (66\%) to considerable weaknesses in phonology (31\%) and morphology (36\%). Through human preference evaluation with 95 annotators, we demonstrate a strong correlation between KoBALT scores and human judgments, validating our benchmark's effectiveness as a discriminative measure of Korean language understanding. KoBALT addresses critical gaps in linguistic evaluation for typologically diverse languages and provides a robust framework for assessing genuine linguistic competence in Korean language models.

Jean Seo, Jaeyoon Kim, SungJoo Byun et al.

The necessity of language-specific tokenizers intuitively appears crucial for effective natural language processing, yet empirical analyses on their significance and underlying reasons are lacking. This study explores how language-specific tokenizers influence the behavior of Large Language Models predominantly trained with English text data, through the case study of Korean. The research unfolds in two main stages: (1) the development of a Korean-specific extended tokenizer and (2) experiments to compare models with the basic tokenizer and the extended tokenizer through various Next Token Prediction tasks. Our in-depth analysis reveals that the extended tokenizer decreases confidence in incorrect predictions during generation and reduces cross-entropy in complex tasks, indicating a tendency to produce less nonsensical outputs. Consequently, the extended tokenizer provides stability during generation, potentially leading to higher performance in downstream tasks.

Guoyuan An, JaeYoon Kim, SungEui Yoon

This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition accuracy, even on benchmarks like ImageNet, despite prior evidence that LMMs typically underperform dedicated vision encoders. Second, we analyze the internal behavior of vision reflection and find that the vision-language connector maps visual features into explicit textual concepts, allowing the language model to reason about prediction plausibility using commonsense knowledge. We further observe that replacing a large number of vision tokens with only a few text tokens still enables LLaVA to generate similar answers, suggesting that LMMs may rely primarily on a compact set of distilled textual representations rather than raw vision features. Third, we show that a training-free connector can enhance LMM performance in fine-grained recognition tasks, without extensive feature-alignment training. Together, these findings offer new insights into the explainability of vision-language models and suggest that vision reflection is a promising strategy for achieving robust and interpretable visual recognition.

Jean Seo, Jaeyoon Kim, Hyopil Shin

We propose the Mixture of Frozen Experts (MoFE) architecture, which integrates Parameter-efficient Fine-tuning (PEFT) and the Mixture of Experts (MoE) architecture to enhance both training efficiency and model scalability. By freezing the Feed Forward Network (FFN) layers within the MoE framework, MoFE significantly reduces the number of trainable parameters, improving training efficiency while still allowing for effective knowledge transfer from the expert models. This facilitates the creation of models proficient in multiple domains. We conduct experiments to evaluate the trade-offs between performance and efficiency, compare MoFE with other PEFT methodologies, assess the impact of domain expertise in the constituent models, and determine the optimal training strategy. The results show that, although there may be some trade-offs in performance, the efficiency gains are substantial, making MoFE a reasonable solution for real-world, resource-constrained environments.

Jaeyoon Kim, Yoonki Cho, Taeyoung Kim et al.

Nearest neighbor (NN) graph based visual re-ranking has emerged as a powerful approach for improving retrieval accuracy, offering the advantages of effectively exploring high-dimensional manifolds without requiring additional fine-tuning. However, the effectiveness of NN graph-based re-ranking is fundamentally constrained by the quality of its edge connectivity, as incorrect connections between dissimilar (negative) images frequently occur. This is known as a noisy edge problem, which hinders the re-ranking performance of existing techniques and limits their potential. To remedy this issue, we propose a complementary denoising method based on Continuous Conditional Random Fields (C-CRF) that leverages statistical distances derived from similarity-based distributions. As a pre-processing step for enhancing NN graph-based retrieval, our approach constructs fully connected cliques around each anchor image and employs a novel statistical distance metric to robustly alleviate noisy edges before re-ranking while achieving efficient processing through offline computation. Extensive experimental results demonstrate that our method consistently improves three different NN graph-based re-ranking approaches, yielding significant gains in retrieval accuracy.

JaeYoon Kim, Junyu Xuan, Christy Liang et al.

Offline-to-online reinforcement learning (RL) leverages both pre-trained offline policies and online policies trained for downstream tasks, aiming to improve data efficiency and accelerate performance enhancement. An existing approach, Policy Expansion (PEX), utilizes a policy set composed of both policies without modifying the offline policy for exploration and learning. However, this approach fails to ensure sufficient learning of the online policy due to an excessive focus on exploration with both policies. Since the pre-trained offline policy can assist the online policy in exploiting a downstream task based on its prior experience, it should be executed effectively and tailored to the specific requirements of the downstream task. In contrast, the online policy, with its immature behavioral strategy, has the potential for exploration during the training phase. Therefore, our research focuses on harmonizing the advantages of the offline policy, termed exploitation, with those of the online policy, referred to as exploration, without modifying the offline policy. In this study, we propose an innovative offline-to-online RL method that employs a non-monolithic exploration approach. Our methodology demonstrates superior performance compared to PEX.

JaeYoon Kim, Junyu Xuan, Christy Liang et al.

Unsupervised pre-training has been on the lookout for the virtue of a value function representation referred to as successor features (SFs), which decouples the dynamics of the environment from the rewards. It has a significant impact on the process of task-specific fine-tuning due to the decomposition. However, existing approaches struggle with local optima due to the unified intrinsic reward of exploration and exploitation without considering the linear regression problem and the discriminator supporting a small skill sapce. We propose a novel unsupervised pre-training model with SFs based on a non-monolithic exploration methodology. Our approach pursues the decomposition of exploitation and exploration of an agent built on SFs, which requires separate agents for the respective purpose. The idea will leverage not only the inherent characteristics of SFs such as a quick adaptation to new tasks but also the exploratory and task-agnostic capabilities. Our suggested model is termed Non-Monolithic unsupervised Pre-training with Successor features (NMPS), which improves the performance of the original monolithic exploration method of pre-training with SFs. NMPS outperforms Active Pre-training with Successor Features (APS) in a comparative experiment.

JaeYoon Kim, Junyu Xuan, Christy Liang et al.

Most exploration research on reinforcement learning (RL) has paid attention to `the way of exploration', which is `how to explore'. The other exploration research, `when to explore', has not been the main focus of RL exploration research. The issue of `when' of a monolithic exploration in the usual RL exploration behaviour binds an exploratory action to an exploitational action of an agent. Recently, a non-monolithic exploration research has emerged to examine the mode-switching exploration behaviour of humans and animals. The ultimate purpose of our research is to enable an agent to decide when to explore or exploit autonomously. We describe the initial research of an autonomous multi-mode exploration of non-monolithic behaviour in an options framework. The higher performance of our method is shown against the existing non-monolithic exploration method through comparative experimental results.

JaeYoon Kim, Junyu Xuan, Christy Liang et al.

The high-dimensional or sparse reward task of a reinforcement learning (RL) environment requires a superior potential controller such as hierarchical reinforcement learning (HRL) rather than an atomic RL because it absorbs the complexity of commands to achieve the purpose of the task in its hierarchical structure. One of the HRL issues is how to train each level policy with the optimal data collection from its experience. That is to say, how to synchronize adjacent level policies optimally. Our research finds that a HRL model through the off-policy correction technique of HRL, which trains a higher-level policy with the goal of reflecting a lower-level policy which is newly trained using the off-policy method, takes the critical role of synchronizing both level policies at all times while they are being trained. We propose a novel HRL model supporting the optimal level synchronization using the off-policy correction technique with a deep generative model. This uses the advantage of the inverse operation of a flow-based deep generative model (FDGM) to achieve the goal corresponding to the current state of the lower-level policy. The proposed model also considers the freedom of the goal dimension between HRL policies which makes it the generalized inverse model of the model-free RL in HRL with the optimal synchronization method. The comparative experiment results show the performance of our proposed model.

Seongjae Kang, Jaeyoon Kim, Sung-eui Yoon

In this research, Piano performances have been analyzed only based on visual information. Computer vision algorithms, e.g., Hough transform and binary thresholding, have been applied to find where the keyboard and specific keys are located. At the same time, Convolutional Neural Networks(CNNs) has been also utilized to find whether specific keys are pressed or not, and how much intensity the keys are pressed only based on visual information. Especially for detecting intensity, a new method of utilizing spatial, temporal CNNs model is devised. Early fusion technique is especially applied in temporal CNNs architecture to analyze hand movement. We also make a new dataset for training each model. Especially when finding an intensity of a pressed key, both of video frames and their optical flow images are used to train models to find effectiveness.

Suhyuk Um, Jaeyoon Kim, Dongbo Min

2-D complex Gabor filtering has found numerous applications in the fields of computer vision and image processing. Especially, in some applications, it is often needed to compute 2-D complex Gabor filter bank consisting of the 2-D complex Gabor filtering outputs at multiple orientations and frequencies. Although several approaches for fast 2-D complex Gabor filtering have been proposed, they primarily focus on reducing the runtime of performing the 2-D complex Gabor filtering once at specific orientation and frequency. To obtain the 2-D complex Gabor filter bank output, existing methods are repeatedly applied with respect to multiple orientations and frequencies. In this paper, we propose a novel approach that efficiently computes the 2-D complex Gabor filter bank by reducing the computational redundancy that arises when performing the Gabor filtering at multiple orientations and frequencies. The proposed method first decomposes the Gabor basis kernels to allow a fast convolution with the Gaussian kernel in a separable manner. This enables reducing the runtime of the 2-D complex Gabor filter bank by reusing intermediate results of the 2-D complex Gabor filtering computed at a specific orientation. Furthermore, we extend this idea into 2-D localized sliding discrete Fourier transform (SDFT) using the Gaussian kernel in the DFT computation, which lends a spatial localization ability as in the 2-D complex Gabor filter. Experimental results demonstrate that our method runs faster than state-of-the-arts methods for fast 2-D complex Gabor filtering, while maintaining similar filtering quality.