arXiv subjects

Jisoo Kim

Publications and source records attributed to Jisoo Kim.

At least 19 recordsLinked to original sources

arXiv2026

JointHOI: Jointly Generating Contact Maps Enhances Hand Object Interaction Generation

Text driven hand object interaction (HOI) generation is gaining attention for immersive applications and robotics, yet producing physically plausible interactions remains challenging. Even when individual motions appear natural, small contact errors can cause conspicuous artifacts such as floating and interpenetration. Prior methods mitigate these issues using explicit contact cues or implicit grasp priors, but typically rely on multi stage pipelines and fail to model temporally evolving contact. We present JointHOI, a single stage diffusion framework that jointly generates 3D hand object motion and dynamic, distance based contact maps from text. By treating contact as an auxiliary inner modality, joint generation enables the model to learn contact motion coupling during training. At inference, contact guided sampling enforces consistency between generated contact maps and motion implied geometry, improving temporal stability and reducing penetration and floating. Experiments on GRAB and ARCTIC demonstrate consistent improvements in text adherence and physical plausibility over prior methods.

cs.CV↗

arXiv2026

AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection

Learning robust dexterous grasping requires real-world data that records the physical outcomes of grasp attempts. Such data is hard to obtain at scale: teleoperation yields valid physical outcomes but is slow and operator-biased, while simulation-based generation is cheap and scalable but cannot certify contact validity. A natural solution is to generate candidate grasps and verify them on real hardware, but this scales only if the entire collection loop (perception, execution, labeling, and reset) runs without human intervention. We present AutoDex, an automated real-world data-collection system that closes this loop: for each candidate from a replaceable generator, it localizes the object under severe hand-object occlusion with dense 20-camera perception, executes collision-monitored robot motions, labels lift-and-hold success or failure, and actively resets the object between trials to expose additional candidates across stable poses. The result is a reusable database of physically labeled grasp trials that downstream systems can query by retrieval and feasibility filtering. Using AutoDex, we collect 3,593 grasp trials across Allegro and Inspire hands on 100 diverse objects, with synchronized multi-view observations and robot-state logs. For a matched 500-trajectory collection, AutoDex requires 10.3 h versus 49.4 h for teleoperation, yielding a 4.8x throughput improvement, and grasps retrieved from the AutoDex-validated database succeed 76% versus 34% for simulation-only validation. Code and data will be publicly released.

cs.RO↗

arXiv2026

Scaling up fine-grained intracranial vessel annotations in computed tomography angiography

In this work, we present SemanticVessel, a dataset for fine-grained brain vessel segmentation in computed tomography angiography scans. Based on the detailed contrast provided by dynamic 4D-CTA scans, we generate segmentation traces for arteries and veins. We then use intensity-guided region growing to obtain segmentations of the majority of vascular territories in the human brain, which are refined and annotated with 20 unique arterial classes by an expert radiologist. Unlike existing datasets, where minor arteries are discarded as background content, we merge these minor arteries into a generic arterial class. Due to the multiple-phase acquisition of dynamic 4D-CTA, labels for a single phase can be re-used for other phases in the same series, greatly increasing the size of our dataset with no additional annotation cost. The results show that models trained with the additional generic artery class produce better fine-grained segmentations across the board. We will make our code, annotation GUI, and model weights available to the scientific community. Code, weights, and data will be made available on https://github.com/alceballosa/robust-vessel-segmentation

eess.IV↗

arXiv2026

ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning

We present ZeroDex, a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images. Rather than training an end-to-end policy, our system uses a vision-language model (VLM) to produce reference-frame task grounding and primitive-level 2D keypoints, then lifts them into 3D via multi-view fusion. This lifting combines triangulation of view-wise VLM groundings with reference-view ray voting, which searches along a semantic camera ray for geometrically consistent candidates across neighboring views. The resulting 3D keypoints support both pick-and-place and tool-use: for tool-use, we retrieve an object-centric atomic action corresponding to the inferred skill category and align its stored 6D tool trajectory to the scene; for dexterous execution, we expand the lifted grasp keypoint into a task-conditioned grasp affordance region and generate feasible grasp-motion pairs with an arm-hand motion generator. Real-world experiments show improved 3D grounding accuracy and execution reliability over single-view RGB-D grounding and fine-tuned VLA baselines. We further demonstrate long-horizon manipulation through closed-loop status verification and replan, enabling zero-shot execution on unseen objects and tool-use tasks in novel scenes.

cs.RO↗

arXiv2026

OmniRobotHome: A Multi-Camera Home Platform for Real-Time Human-Robot Interaction

Robots in homes must continuously sense the people around them, yet most prior work relies on limited or offline perception. We argue that perception quality is the dominant factor governing what interaction is achievable at home, and build a testbed to test this claim. OmniRobotHome instruments a furnished home with 48 hardware-synchronized cameras and three manipulators in a unified world frame, delivering real-time markerless full-body human pose, 6D object pose, anticipatory motion forecasting, and a social avatar agent that converses with residents. Using the platform, we treat perception quality as an experimental variable across safety, human assistance, and social interaction, and find that interaction quality degrades measurably as real-timeness, granularity, coverage, accuracy, forecasting, or memory is weakened. All code and data will be released.

cs.RO↗

arXiv2026

HRDexDB: A Paired Human-Robot Dataset for Cross-Embodiment Dexterous Grasping

We present HRDexDB, a paired cross-embodiment dexterous grasping dataset of high-fidelity dexterous grasping sequences featuring both human and diverse robotic hands. Unlike existing datasets, HRDexDB provides a comprehensive collection of grasping trajectories across human hands and multiple robot hand embodiments, spanning 100 diverse objects. Leveraging state-of-the-art vision methods and a dedicated multi-camera system, HRDexDB offers high-precision spatiotemporal 3D ground-truth motion for both the agent and the manipulated object. The dataset comprises 2.1K grasping trials, each enriched with synchronized visual and kinematic modalities, with contact-force signals available for tactile-enabled robotic hands. By providing closely aligned captures of human dexterity and robotic execution on the same target objects under comparable grasping motions, HRDexDB serves as a foundational benchmark for cross-embodiment dexterous manipulation.

cs.RO↗

arXiv2026

Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation

Humans learn not only how their bodies move, but also how the surrounding world responds to their actions. In contrast, while recent Vision-Language-Action (VLA) models exhibit impressive semantic understanding, they often fail to capture the spatiotemporal dynamics governing physical interaction. In this paper, we introduce Pri4R, a simple yet effective approach that endows VLA models with an implicit understanding of world dynamics by leveraging privileged 4D information during training. Specifically, Pri4R augments VLAs with a lightweight point track head that predicts 3D point tracks. By injecting VLA features into this head to jointly predict future 3D trajectories, the model learns to incorporate evolving scene geometry within its shared representation space, enabling more physically aware context for precise control. Due to its architectural simplicity, Pri4R is compatible with dominant VLA design patterns with minimal changes. During inference, we run the model using the original VLA architecture unchanged; Pri4R adds no extra inputs, outputs, or computational overhead. Across simulation and real-world evaluations, Pri4R significantly improves performance on challenging manipulation tasks, including a +10% gain on LIBERO-Long and a +40% gain on RoboCasa. We further show that 3D point track prediction is an effective supervision target for learning action-world dynamics, and validate our design choices through extensive ablations. Project page: https://jiiiisoo.github.io/Pri4R/

cs.CV↗

arXiv2026

Robust automatic brain vessel segmentation in 3D CTA scans using dynamic 4D-CTA data

In this study, we develop a novel methodology for annotating the brain vasculature using dynamic 4D-CTA head scans. By using multiple time points from dynamic CTA acquisitions, we subtract bone and soft tissue to enhance the visualization of arteries and veins, reducing the effort required to obtain manual annotations of brain vessels. We then train deep learning models on our ground truth annotations by using the same segmentation for multiple phases from the dynamic 4D-CTA collection, effectively enlarging our dataset by 4 to 5 times and inducing robustness to contrast phases. In total, our dataset comprises 110 training images from 25 patients and 165 test images from 14 patients. In comparison with two similarly-sized datasets for CTA-based brain vessel segmentation, a nnUNet model trained on our dataset can achieve significantly better segmentations across all vascular regions, with an average mDC of 0.846 for arteries and 0.957 for veins in the TopBrain dataset. Furthermore, metrics such as average directed Hausdorff distance (adHD) and topology sensitivity (tSens) reflected similar trends: using our dataset resulted in low error margins (adHD of 0.304 mm for arteries and 0.078 for veins) and high sensitivity (tSens of 0.877 for arteries and 0.974 for veins), indicating excellent accuracy in capturing vessel morphology. Our code and model weights are available online at https://github.com/alceballosa/robust-vessel-segmentation

cs.CV↗

arXiv2025

SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion

Human motion is inherently diverse and semantically rich, while also shaped by the surrounding scene. However, existing motion generation approaches fail to generate semantically diverse motion while simultaneously respecting geometric scene constraints, since constructing large-scale datasets with both rich text-motion coverage and precise scene interactions is extremely challenging. In this work, we introduce SceneAdapt, a two-stage adaptation framework that enables semantically diverse, scene-aware human motion generation from text without large-scale paired text--scene--motion data. Our key idea is to use motion inbetweening, a learnable proxy task that requires no text, as a bridge between two disjoint resources: a text-motion dataset and a scene-motion dataset. By first adapting a text-to-motion model through inbetweening and then through scene-aware inbetweening, SceneAdapt injects geometric scene constraints into text-conditioned generation while preserving semantic diversity. To enable adaptation for inbetweening, we propose a novel Context-aware Keyframing (CaKey) layer that modulates motion latents for keyframe-conditioned synthesis while preserving the original latent manifold. To further adapt the model for scene-aware inbetweening, we introduce a Scene-conditioning (SceneCo) layer that injects geometric scene information by adaptively querying local context via cross-attention. Experimental results show that SceneAdapt effectively injects scene-awareness into text-to-motion models without sacrificing semantic diversity, and we further analyze the mechanisms through which this awareness emerges. Code and models will be released. Project page: \href{https://sceneadapt.github.io/}{sceneadapt.github.io}

cs.CV↗

arXiv2025

GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation

Parameter-efficient fine-tuning (PEFT) has become a popular way to adapt large pre-trained models to new tasks. Most PEFT methods update only a small subset of parameters while freezing the rest, avoiding redundant computation. As they maximize the absolute size of the updates without regard to the parameters' original scale, the resulting changes in model behavior can be minimal. In contrast, we maximize updates relative to each parameter's scale, yielding more meaningful downstream adaptation. We propose Gradient-to-Weight Ratio and Entropy-guided Masking (GEM), a parameter scale-aware, distribution-sensitive sparse fine-tuning framework. GEM prioritizes parameters whose updates are significant in proportion to their initial pre-trained values. It also adaptively determines how many parameters to tune at each layer based on the entropy of parameter values, thereby making the most effective use of the computational budget in PEFT. Our empirical study demonstrates the efficacy of GEM on both general-domain tasks (GLUE and SuperGLUE) and domain-specific tasks (GSM8k and MBPP), achieving up to a 1.6% improvement in fine-tuning accuracy over full fine-tuning while updating only 0.1% of model parameters.

cs.LG↗

arXiv2025

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models

With growing interest in deploying text-to-video (T2V) models in resource-constrained environments, reducing their high computational cost has become crucial, leading to extensive research on pruning and knowledge distillation methods while maintaining performance. However, existing distillation methods primarily rely on supervised fine-tuning (SFT), which often leads to mode collapse as pruned models with reduced capacity fail to directly match the teacher's outputs, ultimately resulting in degraded quality. To address this challenge, we propose an effective distillation method, ReDPO, that integrates DPO and SFT. Our approach leverages DPO to guide the student model to focus on recovering only the targeted properties, rather than passively imitating the teacher, while also utilizing SFT to enhance overall performance. We additionally propose V.I.P., a novel framework for filtering and curating high-quality pair datasets, along with a step-by-step online approach for calibrated training. We validate our method on two leading T2V models, VideoCrafter2 and AnimateDiff, achieving parameter reduction of 36.2% and 67.5% each, while maintaining or even surpassing the performance of full models. Further experiments demonstrate the effectiveness of both ReDPO and V.I.P. framework in enabling efficient and high-quality video generation. Our code and videos are available at https://jiiiisoo.github.io/VIP.github.io/.

cs.CV↗

arXiv2025

Automated anatomy-based post-processing reduces false positives and improved interpretability of deep learning intracranial aneurysm detection

Introduction: Deep learning (DL) models can help detect intracranial aneurysms on CTA, but high false positive (FP) rates remain a barrier to clinical translation, despite improvement in model architectures and strategies like detection threshold tuning. We employed an automated, anatomy-based, heuristic-learning hybrid artery-vein segmentation post-processing method to further reduce FPs. Methods: Two DL models, CPM-Net and a deformable 3D convolutional neural network-transformer hybrid (3D-CNN-TR), were trained with 1,186 open-source CTAs (1,373 annotated aneurysms), and evaluated with 143 held-out private CTAs (218 annotated aneurysms). Brain, artery, vein, and cavernous venous sinus (CVS) segmentation masks were applied to remove possible FPs in the DL outputs that overlapped with: (1) brain mask; (2) vein mask; (3) vein more than artery masks; (4) brain plus vein mask; (5) brain plus vein more than artery masks. Results: CPM-Net yielded 139 true-positives (TP); 79 false-negative (FN); 126 FP. 3D-CNN-TR yielded 179 TP; 39 FN; 182 FP. FPs were commonly extracranial (CPM-Net 27.3%; 3D-CNN-TR 42.3%), venous (CPM-Net 56.3%; 3D-CNN-TR 29.1%), arterial (CPM-Net 11.9%; 3D-CNN-TR 53.3%), and non-vascular (CPM-Net 25.4%; 3D-CNN-TR 9.3%) structures. Method 5 performed best, reducing CPM-Net FP by 70.6% (89/126) and 3D-CNN-TR FP by 51.6% (94/182), without reducing TP, lowering the FP/case rate from 0.88 to 0.26 for CPM-NET, and from 1.27 to 0.62 for the 3D-CNN-TR. Conclusion: Anatomy-based, interpretable post-processing can improve DL-based aneurysm detection model performance. More broadly, automated, domain-informed, hybrid heuristic-learning processing holds promise for improving the performance and clinical acceptance of aneurysm detection models.

eess.IV↗

arXiv2025

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues

Nonverbal communication is integral to human interaction, with gestures, facial expressions, and body language conveying critical aspects of intent and emotion. However, existing large language models (LLMs) fail to effectively incorporate these nonverbal elements, limiting their capacity to create fully immersive conversational experiences. We introduce MARS, a multimodal language model designed to understand and generate nonverbal cues alongside text, bridging this gap in conversational AI. Our key innovation is VENUS, a large-scale dataset comprising annotated videos with time-aligned text, facial expressions, and body language. Leveraging VENUS, we train MARS with a next-token prediction objective, combining text with vector-quantized nonverbal representations to achieve multimodal understanding and generation within a unified framework. Based on various analyses of the VENUS datasets, we validate its substantial scale and high effectiveness. Our quantitative and qualitative results demonstrate that MARS successfully generates text and nonverbal languages, corresponding to conversational input.

cs.AI↗

arXiv2025

Light Storage in Light Cages: A Scalable Platform for Multiplexed Quantum Memories

Quantum memories are essential for photonic quantum technologies, enabling long-distance quantum communication and serving as delay units in quantum computing. Hot atomic vapors using electromagnetically induced transparency provide a simple platform with second-long photon storage capabilities. Light-guiding structures enhance performance, but current hollow-core fiber waveguides face significant limitations in filling time, physical size, fabrication versatility, and large-scale integration potential. In this work, we demonstrate the storage of attenuated coherent light pulses in a cesium (Cs) quantum memory based on a 3D-nanoprinted hollow-core waveguide, known as a light cage (LC), with several hundred nanoseconds of storage times. Leveraging the versatile fabrication process, we successfully integrated multiple LC memories onto a single chip within a Cs vapor cell, achieving consistent performance across all devices. We conducted a detailed investigation into storage efficiency, analyzing memory lifetime and bandwidth. These results represent a significant advancement toward spatially multiplexed quantum memories and have the potential to elevate memory integration to unprecedented levels. We anticipate applications in parallel single-photon synchronization for quantum repeater nodes and photonic quantum computing platforms.

quant-ph↗

arXiv2025

Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning

Expensive communication cost is a common performance bottleneck in Federated Learning (FL), which makes it less appealing in real-world applications. Many communication-efficient FL methods focus on discarding a part of model updates mostly based on gradient magnitude. In this study, we find that recycling previous updates, rather than simply dropping them, more effectively reduces the communication cost while maintaining FL performance. We propose FedLUAR, a Layer-wise Update Aggregation with Recycling scheme for communication-efficient FL. We first define a useful metric that quantifies the extent to which the aggregated gradients influences the model parameter values in each layer. FedLUAR selects a few layers based on the metric and recycles their previous updates on the server side. Our extensive empirical study demonstrates that the update recycling scheme significantly reduces the communication cost while maintaining model accuracy. For example, our method achieves nearly the same AG News accuracy as FedAvg, while reducing the communication cost to just 17%.

cs.LG↗

arXiv2025

Anatomically-guided masked autoencoder pre-training for aneurysm detection

Intracranial aneurysms are a major cause of morbidity and mortality worldwide, and detecting them manually is a complex, time-consuming task. Albeit automated solutions are desirable, the limited availability of training data makes it difficult to develop such solutions using typical supervised learning frameworks. In this work, we propose a novel pre-training strategy using more widely available unannotated head CT scan data to pre-train a 3D Vision Transformer model prior to fine-tuning for the aneurysm detection task. Specifically, we modify masked auto-encoder (MAE) pre-training in the following ways: we use a factorized self-attention mechanism to make 3D attention computationally viable, we restrict the masked patches to areas near arteries to focus on areas where aneurysms are likely to occur, and we reconstruct not only CT scan intensity values but also artery distance maps, which describe the distance between each voxel and the closest artery, thereby enhancing the backbone's learned representations. Compared with SOTA aneurysm detection models, our approach gains +4-8% absolute Sensitivity at a false positive rate of 0.5. Code and weights will be released.

cs.CV↗

arXiv2025

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce EgoSpeak, a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker's first-person viewpoint, EgoSpeak is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk. Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that EgoSpeak outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak.

cs.CV↗

arXiv2025

Dynamic-Computed Tomography Angiography for Cerebral Vessel Templates and Segmentation

Background: Computed Tomography Angiography (CTA) is crucial for cerebrovascular disease diagnosis. Dynamic CTA is a type of imaging that captures temporal information about the We aim to develop and evaluate two segmentation techniques to segment vessels directly on CTA images: (1) creating and registering population-averaged vessel atlases and (2) using deep learning (DL). Methods: We retrieved 4D-CT of the head from our institutional research database, with bone and soft tissue subtracted from post-contrast images. An Advanced Normalization Tools pipeline was used to create angiographic atlases from 25 patients. Then, atlas-driven ROIs were identified by a CT attenuation threshold to generate segmentation of the arteries and veins using non-linear registration. To create DL vessel segmentations, arterial and venous structures were segmented using the MRA vessel segmentation tool, iCafe, in 29 patients. These were then used to train a DL model, with bone-in CT images as input. Multiple phase images in the 4D-CT were used to increase the training and validation dataset. Both segmentation approaches were evaluated on a test 4D-CT dataset of 11 patients which were also processed by iCafe and validated by a neuroradiologist. Specifically, branch-wise segmentation accuracy was quantified with 20 labels for arteries and one for veins. DL outperformed the atlas-based segmentation models for arteries (average modified dice coefficient (amDC) 0.856 vs. 0.324) and veins (amDC 0.743 vs. 0.495) overall. For ICAs, vertebral and basilar arteries, DL and atlas -based segmentation had an amDC of 0.913 and 0.402, respectively. The amDC for MCA-M1, PCA-P1, and ACA-A1 segments were 0.932 and 0.474, respectively. Conclusion: Angiographic CT templates are developed for the first time in literature. Using 4D-CTA enables the use of tools like iCafe, lessening the burden of manual annotation.

physics.med-ph↗