arXiv subjects

Sebin Lee

Publications and source records attributed to Sebin Lee.

15 recordsLinked to original sources

arXiv2026

CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics

Robotic manipulation involves kinematic and semantic transitions that are inherently coupled via underlying actions. However, existing approaches plan within either semantic or latent space without explicitly aligning these cross-modal transitions. To address this, we propose CLaD, a framework that models how proprioceptive and semantic states jointly evolve under actions through asymmetric cross-attention that allows kinematic transitions to query semantic ones. CLaD predicts grounded latent foresights via self-supervised objectives with EMA target encoders and auxiliary reconstruction losses, preventing representation collapse while anchoring predictions to observable states. Predicted foresights are modulated with observations to condition a diffusion policy for action generation. On LIBERO-LONG benchmark, CLaD achieves 94.7\% success rate, competitive with large VLAs with significantly fewer parameters.

cs.RO↗

arXiv2026

Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering

Rapidly-exploring random trees (RRTs) have been widely adopted for robot motion planning due to their robustness and theoretical guarantees. However, existing RRT-based planners require explicit goal configurations specified as numerical joint angles, while many practical applications provide goal specifications through visual observations such as images or demonstration videos where precise goal configurations are unavailable. In this paper, we propose visual-RRT (vRRT), a motion planner that enables visual-goal planning by unifying gradient-based exploitation from differentiable robot rendering with sampling-based exploration from RRTs. We further introduce (i) a frontier-based exploration-exploitation strategy that adaptively prioritizes visually promising search regions, and (ii) inertial gradient tree expansion that inherits optimization states across tree branches for momentum-consistent gradient exploitation. Extensive experiments across various robot manipulators including Franka, UR5e, and Fetch demonstrate that vRRT achieves effective visual-goal planning in both simulated and real-world settings, bridging the gap between sampling-based planning and vision-centric robot applications. Our code is available at https://sgvr.kaist.ac.kr/Visual-RRT.

cs.RO↗

arXiv2026

Beyond the Patch: Exploring Vulnerabilities of Visuomotor Policies via Viewpoint-Consistent 3D Adversarial Object

Neural network-based visuomotor policies enable robots to perform manipulation tasks but remain susceptible to perceptual attacks. For example, conventional 2D adversarial patches are effective under fixed-camera setups, where appearance is relatively consistent; however, their efficacy often diminishes under dynamic viewpoints from moving cameras, such as wrist-mounted setups, due to perspective distortions. To proactively investigate potential vulnerabilities beyond 2D patches, this work proposes a viewpoint-consistent adversarial texture optimization method for 3D objects through differentiable rendering. As optimization strategies, we employ Expectation over Transformation (EOT) with a Coarse-to-Fine (C2F) curriculum, exploiting distance-dependent frequency characteristics to induce textures effective across varying camera-object distances. We further integrate saliency-guided perturbations to redirect policy attention and design a targeted loss that persistently drives robots toward adversarial objects. Our comprehensive experiments show that the proposed method is effective under various environmental conditions, while confirming its black-box transferability and real-world applicability.

cs.RO↗

arXiv2026

Hybrid Quantum Temporal Convolutional Networks

Quantum machine learning models for sequential data face scalability challenges with complex multivariate signals. We introduce the Hybrid Quantum Temporal Convolutional Network (HQTCN), which combines classical temporal windowing with a quantum convolutional neural network core. By applying a shared quantum circuit across temporal windows, HQTCN captures long-range dependencies while achieving significant parameter reduction. Evaluated on synthetic NARMA sequences and high-dimensional EEG time-series, HQTCN performs competitively with classical baselines on univariate data and outperforms all baselines on multivariate tasks. The model demonstrates particular strength under data-limited conditions, maintaining high performance with substantially fewer parameters than conventional approaches. These results establish HQTCN as a parameter-efficient approach for multivariate time-series analysis.

cs.LG↗

arXiv2026

MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos

Transferring articulated motion from monocular videos to rigged 3D characters is challenging due to pose ambiguity in 2D observations and morphological differences between source and target. Existing approaches often follow a reconstruct-then-retarget paradigm, tying transfer quality to intermediate 3D reconstruction and limiting applicability to categories with parametric templates. We propose MorphGS, a framework that formulates motion retargeting as a target-driven analysis-by-synthesis problem, directly optimizing target morphology and pose through image-space supervision. A rig-coupled morphology parameterization factorizes character identity from time-varying joint rotations, while dense 2D-3D correspondences and synthesized views provide complementary structural and multi-view guidance. Experiments on synthetic benchmarks and real-world videos show consistent improvements over baselines. Project page: https://xodus777.github.io/MorphGS/

cs.CV↗

arXiv2025

DIVER-1: Scaling Intracranial EEG Foundation Models for Transferable Representations

Intracranial EEG (iEEG) provides direct, millisecond-scale recordings of human neural activity, but reusable representation learning is difficult because electrode layouts, anatomical coverage, referencing schemes, and recording conditions vary across patients and centers. We introduce DIVER-1, a self-supervised iEEG foundation model for variable-input recordings that combines any-variate electrode-time attention, spatio-temporal resampling, input-conditioned positional embeddings, and multi-domain masked reconstruction without assuming a fixed electrode montage. We pretrain two variants, DIVER-1-0.1s and DIVER-1-1s, on 5,310 hours of ECoG and SEEG spanning 352k channel-hours, roughly 54x the BrainTreeBank-based pretraining volume. We evaluate DIVER-1 on two held-out benchmarks: Neuroprobe for naturalistic cognitive decoding and MAYO for seizure detection. On leakage-aware Neuroprobe, DIVER-1-0.1s outperforms prior evaluated iEEG foundation models despite using no BrainTreeBank recordings, the corpus underlying Neuroprobe, during pretraining; it also exceeds the linear spectrogram decoder in mean AUROC and remains competitive with stronger nonlinear baselines, a level prior evaluated iEEG foundation models did not reach. DIVER-1-1s also achieves the top AUROC on MAYO seizure detection. Finally, we conduct, to our knowledge, the first controlled compute-aware scaling study for self-supervised iEEG pretraining, sweeping data scale, subject count, training duration, and model size up to 1.8B parameters. Our results indicate a data-constrained regime: expanding unique recordings and training sufficiently long are more reliable scaling axes than increasing parameter count alone. Code is available at link.

cs.LG↗

arXiv2025

DIVER-0 : A Fully Channel Equivariant EEG Foundation Model

Electroencephalography (EEG) is a non-invasive technique widely used in brain-computer interfaces and clinical applications, yet existing EEG foundation models face limitations in modeling spatio-temporal brain dynamics and lack channel permutation equivariance, preventing robust generalization across diverse electrode configurations. To address these challenges, we propose DIVER-0, a novel EEG foundation model that demonstrates how full spatio-temporal attention-rather than segregated spatial or temporal processing-achieves superior performance when properly designed with Rotary Position Embedding (RoPE) for temporal relationships and binary attention biases for channel differentiation. We also introduce Sliding Temporal Conditional Positional Encoding (STCPE), which improves upon existing conditional positional encoding approaches by maintaining both temporal translation equivariance and channel permutation equivariance, enabling robust adaptation to arbitrary electrode configurations unseen during pretraining. Experimental results demonstrate that DIVER-0 achieves competitive performance with only 10% of pretraining data while maintaining consistent results across all channel permutation conditions, validating its effectiveness for cross-dataset generalization and establishing key design principles for handling the inherent heterogeneity of neural recording setups.

eess.SP↗

arXiv2025

Concert Interaction Translation: Augmenting VR Live Concert Experience using Chat-Driven Artificial Collective Reactions

Computer-mediated concerts can be enjoyed on various devices, from desktop and mobile to VR devices, often supporting multiple devices simultaneously. However, due to the limited accessibility of VR devices, relatively small audience members tend to congregate in VR venues, resulting in diminished unique social experiences. To address this gap and enrich VR concert experiences, we present a novel approach that leverages non-VR user interaction data, specifically chat from audiences watching the same content on a live-streaming platform. Based on an analysis of audience reactions in offline concerts, we designed and prototyped a concert interaction translation system that extracts the level of engagement and emotions from chats and translates them to collective movements, cheers, and singalongs of virtual audience avatars in a VR venue. Our user study (n=48) demonstrates that our system, which combines both movement and audio reactions, significantly enhances the sense of immersion and co-presence than the previous method.

cs.HC↗

arXiv2025

VTuber's Atelier: The Design Space, Challenges, and Opportunities for VTubing

VTubing, the practice of live streaming using virtual avatars, has gained worldwide popularity among streamers seeking to maintain anonymity. While previous research has primarily focused on the social and cultural aspects of VTubing, there is a noticeable lack of studies examining the practical challenges VTubers face in creating and operating their avatars. To address this gap, we surveyed VTubers' equipment and expanded the live-streaming design space by introducing six new dimensions related to avatar creation and control. Additionally, we conducted interviews with 16 professional VTubers to comprehensively explore their practices, strategies, and challenges throughout the VTubing process. Our findings reveal that VTubers face significant burdens compared to real-person streamers due to fragmented tools and the multi-tasking nature of VTubing, leading to unique workarounds. Finally, we summarize these challenges and propose design opportunities to improve the effectiveness and efficiency of VTubing.

cs.HC↗

arXiv2024

Regularizing Dynamic Radiance Fields with Kinematic Fields

This paper presents a novel approach for reconstructing dynamic radiance fields from monocular videos. We integrate kinematics with dynamic radiance fields, bridging the gap between the sparse nature of monocular videos and the real-world physics. Our method introduces the kinematic field, capturing motion through kinematic quantities: velocity, acceleration, and jerk. The kinematic field is jointly learned with the dynamic radiance field by minimizing the photometric loss without motion ground truth. We further augment our method with physics-driven regularizers grounded in kinematics. We propose physics-driven regularizers that ensure the physical validity of predicted kinematic quantities, including advective acceleration and jerk. Additionally, we control the motion trajectory based on rigidity equations formed with the predicted kinematic quantities. In experiments, our method outperforms the state-of-the-arts by capturing physical motion patterns within challenging real-world monocular videos.

cs.CV↗

arXiv2024

Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation

Audio-visual segmentation (AVS) aims to segment sound sources in the video sequence, requiring a pixel-level understanding of audio-visual correspondence. As the Segment Anything Model (SAM) has strongly impacted extensive fields of dense prediction problems, prior works have investigated the introduction of SAM into AVS with audio as a new modality of the prompt. Nevertheless, constrained by SAM's single-frame segmentation scheme, the temporal context across multiple frames of audio-visual data remains insufficiently utilized. To this end, we study the extension of SAM's capabilities to the sequence of audio-visual scenes by analyzing contextual cross-modal relationships across the frames. To achieve this, we propose a Spatio-Temporal, Bidirectional Audio-Visual Attention (ST-BAVA) module integrated into the middle of SAM's image encoder and mask decoder. It adaptively updates the audio-visual features to convey the spatio-temporal correspondence between the video frames and audio streams. Extensive experiments demonstrate that our proposed model outperforms the state-of-the-art methods on AVS benchmarks, especially with an 8.3% mIoU gain on a challenging multi-sources subset.

cs.CV↗

arXiv2024

SemCity: Semantic Scene Generation with Triplane Diffusion

We present "SemCity," a 3D diffusion model for semantic scene generation in real-world outdoor environments. Most 3D diffusion models focus on generating a single object, synthetic indoor scenes, or synthetic outdoor scenes, while the generation of real-world outdoor scenes is rarely addressed. In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset. In contrast to synthetic data, real-outdoor datasets often contain more empty spaces due to sensor limitations, causing challenges in learning real-outdoor distributions. To address this issue, we exploit a triplane representation as a proxy form of scene distributions to be learned by our diffusion model. Furthermore, we propose a triplane manipulation that integrates seamlessly with our triplane diffusion model. The manipulation improves our diffusion model's applicability in a variety of downstream tasks related to outdoor scene generation such as scene inpainting, scene outpainting, and semantic scene completion refinements. In experimental results, we demonstrate that our triplane diffusion model shows meaningful generation results compared with existing work in a real-outdoor dataset, SemanticKITTI. We also show our triplane manipulation facilitates seamlessly adding, removing, or modifying objects within a scene. Further, it also enables the expansion of scenes toward a city-level scale. Finally, we evaluate our method on semantic scene completion refinements where our diffusion model enhances predictions of semantic scene completion networks by learning scene distribution. Our code is available at https://github.com/zoomin-lee/SemCity.

cs.CV↗

arXiv2023

Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data

In this paper, we learn a diffusion model to generate 3D data on a scene-scale. Specifically, our model crafts a 3D scene consisting of multiple objects, while recent diffusion research has focused on a single object. To realize our goal, we represent a scene with discrete class labels, i.e., categorical distribution, to assign multiple objects into semantic categories. Thus, we extend discrete diffusion models to learn scene-scale categorical distributions. In addition, we validate that a latent diffusion model can reduce computation costs for training and deploying. To the best of our knowledge, our work is the first to apply discrete and latent diffusion for 3D categorical data on a scene-scale. We further propose to perform semantic scene completion (SSC) by learning a conditional distribution using our diffusion model, where the condition is a partial observation in a sparse point cloud. In experiments, we empirically show that our diffusion models not only generate reasonable scenes, but also perform the scene completion task better than a discriminative model. Our code and models are available at https://github.com/zoomin-lee/scene-scale-diffusion

cs.CV↗

arXiv2022

Semi-Supervised Learning of Optical Flow by Flow Supervisor

A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset. However, obtaining ground truth flows from a target video requires a tremendous effort. This paper proposes a practical fine tuning method to adapt a pretrained model to a target dataset without ground truth flows, which has not been explored extensively. Specifically, we propose a flow supervisor for self-supervision, which consists of parameter separation and a student output connection. This design is aimed at stable convergence and better accuracy over conventional self-supervision methods which are unstable on the fine tuning task. Experimental results show the effectiveness of our method compared to different self-supervision methods for semi-supervised learning. In addition, we achieve meaningful improvements over state-of-the-art optical flow models on Sintel and KITTI benchmarks by exploiting additional unlabeled datasets. Code is available at https://github.com/iwbn/flow-supervisor.

cs.CV↗

arXiv2020

Dynamic Humanoid Locomotion over Uneven Terrain With Streamlined Perception-Control Pipeline

Although bipedal locomotion provides the ability to traverse unstructured environments, it requires careful planning and control to safely walk across without falling. This poses an integrated challenge for the robot to perceive, plan, and control its movements, especially with dynamic motions where the robot may have to adapt its swing-leg trajectory onthe-fly in order to safely place its foot on the uneven terrain. In this paper we present an efficient geometric footstep planner and the corresponding walking controller that enables a humanoid robot to dynamically walk across uneven terrain at speeds up to 0.3 m/s. As dynamic locomotion, we refer first to the continuous walking motion without stopping, and second to the on-the-fly replanning of the landing footstep position in middle of the swing phase during the robot gait cycle. This is mainly achieved through the streamlined integration between an efficient sampling-based planner and robust walking controller. The footstep planner is able to generate feasible footsteps within 5 milliseconds, and the controller is able to generate a new corresponding swing leg trajectory as well as the wholebody motion to dynamically balance the robot to the newly updated footsteps. The proposed perception-control pipeline is evaluated and demonstrated with real experiments using a fullscale humanoid to traverse across uneven terrains featured by static stepping stones, dynamically movable stepping stone, or narrow path.

cs.RO↗