arXiv subjects

Jaein Kim

Publications and source records attributed to Jaein Kim.

14 recordsLinked to original sources

arXiv2026

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment

The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence. However, a detailed understanding of component-wise quantization remains a bottleneck for optimal deployment. This paper presents a systematic evaluation framework for empirically validating five hypotheses across six quantization configurations on the Jetson Orin NX and AGX. By separating the vision encoder, projector, and large language model backbone yields the following results: (1) Quantization sensitivity is governed by the structural paradigm (MoE vs. dense) rather than scale alone, with MoE backbones mitigating INT4 noise where dense backbones degrade; (2) SigLIP encoders incur disproportionate INT8 latency on Jetson Ampere--a deployment-specific encoder-kernel-hardware interaction, not a SigLIP flaw; (3) Although INT4 quantization of LLMs greatly reduces VRAM consumption, it also causes slower token generation due to dequantization overhead; (4) Composite quantization errors are largely additive, except along the modality-alignment path, which is architecture-dependent; (5) The intelligence-per-joule profile varies significantly across platforms owing to memory bandwidth constraints.

cs.LG↗

arXiv2026

Learning Coordinate-based Convolutional Kernels for Continuous SE(3) Equivariant and Efficient Point Cloud Analysis

A symmetry on rigid motion is one of the salient factors in efficient learning of 3D point cloud problems. Group convolution has been a representative method to extract equivariant features, but its realizations have struggled to retain both rigorous symmetry and scalability simultaneously. We advocate utilizing the intertwiner framework to resolve this trade-off, but previous works on it, which did not achieve complete SE(3) symmetry or scalability to large-scale problems, necessitate a more advanced kernel architecture. We present Equivariant Coordinate-based Kernel Convolution, or ECKConv. It acquires SE(3) equivariance from the kernel domain defined in a double coset space, and its explicit kernel design using coordinate-based networks enhances its learning capability and memory efficiency. The experiments on diverse point cloud tasks, e.g., classification, pose registration, part segmentation, and large-scale semantic segmentation, validate the rigid equivariance, memory scalability, and outstanding performance of ECKConv compared to state-of-the-art equivariant methods.

cs.CV↗

arXiv2026

Voronoi-based Second-order Descriptor with Whitened Metric in LiDAR Place Recognition

The pooling layer plays a vital role in aggregating local descriptors into the metrizable global descriptor in the LiDAR Place Recognition (LPR). In particular, the second-order pooling is capable of capturing higher-order interactions among local descriptors. However, its existing methods in the LPR adhere to conventional implementations and post-normalization, and incur the descriptor unsuitable for Euclidean distancing. Based on the recent interpretation that associates NetVLAD with the second-order statistics, we propose to integrate second-order pooling with the inductive bias from Voronoi cells. Our novel pooling method aggregates local descriptors to form the second-order matrix and whitens the global descriptor to implicitly measure the Mahalanobis distance while conserving the cluster property from Voronoi cells, addressing its numerical instability during learning with diverse techniques. We demonstrate its performance gains through the experiments conducted on the Oxford Robotcar and Wild-Places benchmarks and analyze the numerical effect of the proposed whitening algorithm.

cs.CV↗

arXiv2025

DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting

Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Existing novel view synthesis methods are often constrained by their reliance on high-resolution images or strong assumptions about static geometry and rigid scene priors. Consequently, their approaches lack robustness in real-world environments with dynamic object and camera motion, leading to instability and degraded visual fidelity. To address this, we propose Motion-aware Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting (DBMovi-GS), a method designed for dynamic view synthesis from blurry monocular videos. Our model generates dense 3D Gaussians, restoring sharpness from blurry videos and reconstructing detailed 3D geometry of the scene affected by dynamic motion variations. Our model achieves robust performance in novel view synthesis under dynamic blurry scenes and sets a new benchmark in realistic novel view synthesis for blurry monocular video inputs.

cs.CV↗

arXiv2025

Variational Online Mirror Descent for Robust Learning in Schr\"odinger Bridge

The Schr\"{o}dinger bridge (SB) has evolved into a universal class of probabilistic generative models. In practice, however, estimated learning signals are innately uncertain, and the reliability promised by existing methods is often based on speculative optimal case scenarios. Recent studies regarding the Sinkhorn algorithm through mirror descent (MD) have gained attention, revealing geometric insights into solution acquisition of the SB problems. In this paper, we propose a variational online MD (OMD) framework for the SB problems, which provides further stability to SB solvers. We formally prove convergence and a regret bound for the novel OMD formulation of SB acquisition. As a result, we propose a simulation-free SB algorithm called Variational Mirrored Schr\"{o}dinger Bridge (VMSB) by utilizing the Wasserstein-Fisher-Rao geometry of the Gaussian mixture parameterization for Schr\"{o}dinger potentials. Based on the Wasserstein gradient flow theory, the algorithm offers tractable learning dynamics that precisely approximate each OMD step. In experiments, we validate the performance of the proposed VMSB algorithm across an extensive suite of benchmarks. VMSB consistently outperforms contemporary SB solvers on a wide range of SB problems, demonstrating the robustness as well as generality predicted by our OMD theory.

cs.LG↗

arXiv2024

Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios

Recent Text-to-SQL methods leverage large language models (LLMs) by incorporating feedback from the database management system. While these methods effectively address execution errors in SQL queries, they struggle with database mismatches -- errors that do not trigger execution exceptions. Database mismatches include issues such as condition mismatches and stricter constraint mismatches, both of which are more prevalent in real-world scenarios. To address these challenges, we propose a tool-assisted agent framework for SQL inspection and refinement, equipping the LLM-based agent with two specialized tools: a retriever and a detector, designed to diagnose and correct SQL queries with database mismatches. These tools enhance the capability of LLMs to handle real-world queries more effectively. We also introduce Spider-Mismatch, a new dataset specifically constructed to reflect the condition mismatch problems encountered in real-world scenarios. Experimental results demonstrate that our method achieves the highest performance on the averaged results of the Spider and Spider-Realistic datasets in few-shot settings, and it significantly outperforms baseline methods on the more realistic dataset, Spider-Mismatch.

cs.CL↗

arXiv2024

Progressively Modality Freezing for Multi-Modal Entity Alignment

Multi-Modal Entity Alignment aims to discover identical entities across heterogeneous knowledge graphs. While recent studies have delved into fusion paradigms to represent entities holistically, the elimination of features irrelevant to alignment and modal inconsistencies is overlooked, which are caused by inherent differences in multi-modal features. To address these challenges, we propose a novel strategy of progressive modality freezing, called PMF, that focuses on alignmentrelevant features and enhances multi-modal feature fusion. Notably, our approach introduces a pioneering cross-modal association loss to foster modal consistency. Empirical evaluations across nine datasets confirm PMF's superiority, demonstrating stateof-the-art performance and the rationale for freezing modalities. Our code is available at https://github.com/ninibymilk/PMF-MMEA.

cs.CL↗

arXiv2024

OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics

Human perception involves decomposing complex multi-object scenes into time-static object appearance (i.e., size, shape, color) and time-varying object motion (i.e., position, velocity, acceleration). For machines to achieve human-like intelligence in real-world interactions, understanding these physical properties of objects is essential, forming the foundation for dynamic video prediction. While recent advancements in object-centric transformers have demonstrated potential in video prediction, they primarily focus on object appearance, often overlooking motion dynamics, which is crucial for modeling dynamic interactions and maintaining temporal consistency in complex environments. To address these limitations, we propose OCK, a dynamic video prediction model leveraging object-centric kinematics and object slots. We introduce a novel component named Object Kinematics that comprises explicit object motions, serving as an additional attribute beyond conventional appearance features to model dynamic scenes. The Object Kinematics are integrated into various OCK mechanisms, enabling spatiotemporal prediction of complex object interactions over long video sequences. Our model demonstrates superior performance in handling complex scenes with intricate object attributes and motions, highlighting its potential for applicability in vision-related dynamics learning tasks.

cs.CV↗

arXiv2023

Anaphor Assisted Document-Level Relation Extraction

Document-level relation extraction (DocRE) involves identifying relations between entities distributed in multiple sentences within a document. Existing methods focus on building a heterogeneous document graph to model the internal structure of an entity and the external interaction between entities. However, there are two drawbacks in existing methods. On one hand, anaphor plays an important role in reasoning to identify relations between entities but is ignored by these methods. On the other hand, these methods achieve cross-sentence entity interactions implicitly by utilizing a document or sentences as intermediate nodes. Such an approach has difficulties in learning fine-grained interactions between entities across different sentences, resulting in sub-optimal performance. To address these issues, we propose an Anaphor-Assisted (AA) framework for DocRE tasks. Experimental results on the widely-used datasets demonstrate that our model achieves a new state-of-the-art performance.

cs.CL↗

arXiv2023

PGA: Personalizing Grasping Agents with Single Human-Robot Interaction

Language-Conditioned Robotic Grasping (LCRG) aims to develop robots that comprehend and grasp objects based on natural language instructions. While the ability to understand personal objects like my wallet facilitates more natural interaction with human users, current LCRG systems only allow generic language instructions, e.g., the black-colored wallet next to the laptop. To this end, we introduce a task scenario GraspMine alongside a novel dataset aimed at pinpointing and grasping personal objects given personal indicators via learning from a single human-robot interaction, rather than a large labeled dataset. Our proposed method, Personalized Grasping Agent (PGA), addresses GraspMine by leveraging the unlabeled image data of the user's environment, called Reminiscence. Specifically, PGA acquires personal object information by a user presenting a personal object with its associated indicator, followed by PGA inspecting the object by rotating it. Based on the acquired information, PGA pseudo-labels objects in the Reminiscence by our proposed label propagation algorithm. Harnessing the information acquired from the interactions and the pseudo-labeled objects in the Reminiscence, PGA adapts the object grounding model to grasp personal objects. This results in significant efficiency while previous LCRG systems rely on resource-intensive human annotations -- necessitating hundreds of labeled data to learn my wallet. Moreover, PGA outperforms baseline methods across all metrics and even shows comparable performance compared to the fully-supervised method, which learns from 9k annotated data samples. We further validate PGA's real-world applicability by employing a physical robot to execute GrsapMine. Code and data are publicly available at https://github.com/JHKim-snu/PGA.

cs.RO↗

arXiv2023

PROGrasp: Pragmatic Human-Robot Communication for Object Grasping

Interactive Object Grasping (IOG) is the task of identifying and grasping the desired object via human-robot natural language interaction. Current IOG systems assume that a human user initially specifies the target object's category (e.g., bottle). Inspired by pragmatics, where humans often convey their intentions by relying on context to achieve goals, we introduce a new IOG task, Pragmatic-IOG, and the corresponding dataset, Intention-oriented Multi-modal Dialogue (IM-Dial). In our proposed task scenario, an intention-oriented utterance (e.g., "I am thirsty") is initially given to the robot. The robot should then identify the target object by interacting with a human user. Based on the task setup, we propose a new robotic system that can interpret the user's intention and pick up the target object, Pragmatic Object Grasping (PROGrasp). PROGrasp performs Pragmatic-IOG by incorporating modules for visual grounding, question asking, object grasping, and most importantly, answer interpretation for pragmatic inference. Experimental results show that PROGrasp is effective in offline (i.e., target object discovery) and online (i.e., IOG with a physical robot arm) settings. Code and data are available at https://github.com/gicheonkang/prograsp.

cs.CL↗

arXiv2023

GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation

Language-Guided Robotic Manipulation (LGRM) is a challenging task as it requires a robot to understand human instructions to manipulate everyday objects. Recent approaches in LGRM rely on pre-trained Visual Grounding (VG) models to detect objects without adapting to manipulation environments. This results in a performance drop due to a substantial domain gap between the pre-training and real-world data. A straightforward solution is to collect additional training data, but the cost of human-annotation is extortionate. In this paper, we propose Grounding Vision to Ceaselessly Created Instructions (GVCCI), a lifelong learning framework for LGRM, which continuously learns VG without human supervision. GVCCI iteratively generates synthetic instruction via object detection and trains the VG model with the generated data. We validate our framework in offline and online settings across diverse environments on different VG models. Experimental results show that accumulating synthetic data from GVCCI leads to a steady improvement in VG by up to 56.7% and improves resultant LGRM by up to 29.4%. Furthermore, the qualitative analysis shows that the unadapted VG model often fails to find correct objects due to a strong bias learned from the pre-training data. Finally, we introduce a novel VG dataset for LGRM, consisting of nearly 252k triplets of image-object-instruction from diverse manipulation environments.

cs.RO↗

arXiv2019

Joint Design of Fronthauling and Hybrid Beamforming for Downlink C-RAN Systems

Hybrid beamforming is known to be a cost-effective and wide-spread solution for a system with large-scale antenna arrays. This work studies the optimization of the analog and digital components of the hybrid beamforming solution for remote radio heads (RRHs) in a downlink cloud radio access network (C-RAN) architecture. Digital processing is carried out at a baseband processing unit (BBU) in the "cloud" and the precoded baseband signals are quantized prior to transmission to the RRHs via finite-capacity fronthaul links. In this system, we consider two different channel state information (CSI) scenarios: 1) ideal CSI at the BBU 2) imperfect effective CSI. Optimization of digital beamforming and fronthaul quantization strategies at the BBU as well as analog radio frequency (RF) beamforming at the RRHs is a coupled problem, since the effect of the quantization noise at the receiver depends on the precoding matrices. The resulting joint optimization problem is examined with the goal of maximizing the weighted downlink sum-rate and the network energy efficiency. Fronthaul capacity and per-RRH power constraints are enforced along with constant modulus constraint on the RF beamforming matrices. For the case of perfect CSI, a block coordinate descent scheme is proposed based on the weighted minimum-mean-square-error approach by relaxing the constant modulus constraint of the analog beamformer. Also, we present the impact of imperfect CSI on the weighted sum-rate and network energy efficiency performance, and the algorithm is extended by applying the sample average approximation. Numerical results confirm the effectiveness of the proposed scheme and show that the proposed algorithm is robust to estimation errors.

cs.IT↗

arXiv2017

Joint Design of Digital and Analog Processing for Downlink C-RAN with Large-Scale Antenna Arrays

In millimeter-wave communication systems with large-scale antenna arrays, conventional digital beamforming may not be cost-effective. A promising solution is the implementation of hybrid beamforming techniques, which consist of low-dimensional digital beamforming followed by analog radio frequency (RF) beamforming. This work studies the optimization of hybrid beamforming in the context of a cloud radio access network (C-RAN) architecture. In a C-RAN system, digital baseband signal processing functionalities are migrated from remote radio heads (RRHs) to a baseband processing unit (BBU) in the "cloud" by means of finite-capacity fronthaul links. Specifically, this work tackles the problem of jointly optimizing digital beamforming and fronthaul quantization strategies at the BBU, as well as RF beamforming at the RRHs, with the goal of maximizing the weighted downlink sum-rate. Fronthaul capacity and per-RRH power constraints are enforced along with constant modulus constraints on the RF beamforming matrices. An iterative algorithm is proposed that is based on successive convex approximation and on the relaxation of the constant modulus constraint. The effectiveness of the proposed scheme is validated by numerical simulation results.

cs.IT↗