arXiv subjects

Seon Joo Kim

Publications and source records attributed to Seon Joo Kim.

At least 19 recordsLinked to original sources

arXiv2026

HuRo: Robotizing Human Videos for Scalable VLA Pretraining

Human video datasets offer an abundant and diverse source of interaction data that can complement expensive real-robot data. To bridge the human-to-robot embodiment gap, existing approaches either robotize videos in task-matched settings or address observation and action alignment separately. In this work, we systematically examine whether robotized human videos can serve as an effective and scalable source of robot-aligned supervision. To this end, we develop a robotization pipeline that converts heterogeneous human videos into robot-aligned observations and action trajectories while inferring missing intermediate signals across annotation levels. Using this pipeline, we construct the HuRo dataset, comprising about 630K robotized episodes and 142M processed frames from five human-video sources. Across four real-world manipulation tasks, pretraining a VLA policy on increasing amounts of robotized human-video data improves overall completion from 51.5% to 80.3% and OOD completion under spatial and visual shifts from 34.9% to 72.2%. Ablations further show that visual robotization improves OOD robustness and that end-to-end pretraining with retargeted actions outperforms visual-only transfer. Project website: https://3587jjh.github.io/HuRo.

cs.RO↗

arXiv2026

Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding

When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs). This ultra-long setting necessitates a two-stage paradigm: query-agnostic memory construction followed by retrieval-based inference. Prior work invests in complex memory construction to pre-model high-level relations in videos, despite not knowing the downstream query at build time. We instead prioritize high-recall retrievability during memory building, and defer query-specific, high-level relation composition to inference time. To this end, we propose MERIT(Multi-key Episodic Retrieval with Inference-time Temporal expansion), a simple yet effective agentic framework for ultra-long video understanding. First, we formulate an episodic multi-key representation that enables precise retrieval of fine-grained memories through a simple key-matching mechanism. Second, we introduce a neighbor filtering mechanism to capture broader semantic context without the massive computational overhead of global memory construction. This is achieved by expanding the temporal scope exclusively around the retrieved segments at inference time. By leveraging simple key-matching with this on-demand temporal expansion, MERIT achieves state-of-the-art performance across three long-video benchmarks: EgoLifeQA, LVBench, and Video-MME (Long).

cs.CV↗

arXiv2026

Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping

We propose DOME-HDR, a dual-output multi-exposure HDR reconstruction framework that jointly produces a perceptually balanced SDR image and a consistent HDR image via gain map inverse tone mapping. Given three bracketed LDR inputs, DOME-HDR first synthesizes a base SDR using a LoRA-adapted latent diffusion model. A dual cross-attention fusion module injects complementary structural and color cues from the under- and over-exposed images while anchoring on the mid exposure for stability. The synthesized SDR then guides HPGM, our HDR Prior-guided Gain Map network, to predict a spatially varying gain map for reliable dynamic-range expansion. We evaluate on Kalantari, Tel, and Challenge123 using both full-reference and no-reference metrics, where DOME-HDR achieves state-of-the-art HDR reconstruction quality; ablations further confirm the effectiveness of dual cross-attention and SDR-guided gain map estimation.

cs.CV↗

arXiv2026

Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking

Web agents act through long interaction sequences, yet existing benchmarks evaluate only terminal success, discarding all process information and offering little guidance on improvement. In this work, we conduct a process-level analysis of web agents. We introduce WebStep, a benchmark of 1,800 task instances with controlled difficulty and automatic semantic state tracking. Each website exposes a deterministic semantic MDP alongside the GUI: the agent operates on the interface, while the environment records high-level states and transitions in the background, enabling fine-grained analysis without manual annotation. Based on the semantic trajectory, we first show that process metrics reveal differences invisible to outcome evaluation: three agents whose success rates cluster within 34-37% diverge in exploration reach versus execution accuracy. Then, decomposing by skill characterizes the nature of these differences, exposing opposite per-skill rankings hidden within the same website: e.g., on Q&A, Claude CUA outperforms OpenAI CUA by 30% on navigation actions yet underperforms it by 6.7% on inspection, pinpointing a concrete skill to improve even within a domain. Bifurcation analysis further localizes the decisive error that loses the task and shows that this error is agent-specific rather than shared. Finally, these differences widen as tasks grow harder: success rate is similar on easy tasks but separates sharply as exploration becomes more demanding. Our process-level analysis opens a new avenue in web agent evaluation, providing fine-grained and actionable insight into where and how each agent should be improved. Project page: https://jiwanchung.github.io/webstep

cs.AI↗

arXiv2026

ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion

3D Gaussian Splatting (3DGS) achieves high-quality novel-view synthesis by optimizing freely placed primitives in 3D and adaptively densifying them in under-reconstructed regions. However, this scene-adaptive capacity allocation is largely lost in existing feed-forward 3DGS methods, which commonly regress Gaussians at input pixels and lift them along camera rays. Such pixel-aligned formulations make the number and placement of primitives depend on image resolution and input viewpoints rather than scene complexity, resulting in dense and often redundant Gaussian sets. We present ATSplat, a feed-forward 3DGS framework that restores the adaptive allocation capability of 3DGS optimization through Adaptive 3D Tokens. ATSplat first lifts coarse patch-level depth and camera cues into sparse 3D anchor tokens, forming a compact scaffold of the scene. Each token is then regressed into local Gaussians with learnable 3D offsets, decoupling primitive placement from input image grids. An Adaptive Token Expansion module predicts a token-level uncertainty score, supervised by rendering error maps, and selectively expands high-uncertainty tokens through learnable expansion layers. This sparse-to-adaptive formulation enables ATSplat to concentrate primitives in challenging regions while maintaining a compact representation. Experiments on two representative datasets, RealEstate10K and DL3DV, show that ATSplat achieves state-of-the-art rendering quality while reducing the number of Gaussians by more than $5.7\times$ compared with dense feed-forward 3DGS methods. From 12 input images at $512 \times 960$ resolution, ATSplat completes reconstruction in less than a second using a single commercial GPU, and renders high-quality novel views at 1136 FPS ($512 \times 960$) with only 311K Gaussians.

cs.CV↗

arXiv2026

Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation

Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture. Combining images taken at different exposure levels requires handling geometric differences while naturally merging their complementary brightness information. It often demands generative completion where details are missing. Diffusion-based generative methods address these challenges, however, they are computationally expensive and struggle to preserve fine structures in saturated regions. We propose LIIFusion, a coarse-to-fine framework that balances fusion quality and efficiency in generative MEF. The coarse stage performs low resolution generative fusion, enhanced by an adaptive exposure correction that recovers structure lost in saturated over-exposed areas. The fine stage adapts a local implicit image function into a multi-exposure fusion function: conditioned on the HR OE/UE sources and the coarse output, it queries arbitrary target coordinates and fuses source evidence regardless of the HR input resolution. LIIFusion achieves up to 3.5$\times$ speed-up over existing generative methods while maintaining or improving structural fidelity and perceptual quality. We believe this framework provides an effective pathway toward making generative MEF more practical in real-world applications.

cs.CV↗

arXiv2026

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

A 3D scene is understood through its objects, not the primitives that compose them. Yet feed-forward reconstruction methods output dense, unstructured sets of points or Gaussians, leaving object-level structure to be recovered after the fact. We propose a feed-forward framework that decomposes a scene into instance-structured 3D token groups directly from unposed multi-view images -- compact object-centric units from which reconstruction, segmentation, and manipulation all follow. Each token group pairs an instance token capturing entity-level identity with anchor tokens that encode local geometry and appearance, which are decoded into a set of 3D Gaussians. This two-level factorization decouples object identity from local appearance, making object instances a native interface of the representation rather than a derived product. The token groups are learned through differentiable rendering with joint reconstruction and segmentation supervision, requiring no 3D annotations. Our feed-forward model surpasses per-scene optimization baselines in class-agnostic instance segmentation while remaining competitive in novel view synthesis. Beyond these metrics, the same token groups directly unlock instance-level scene editing -- removing, translating, or inserting objects by operating on their groups -- as well as efficient open-vocabulary 3D instance retrieval, where retrieval complexity scales with the number of instances rather than primitives.

cs.CV↗

arXiv2026

Global Geometry Is Not Enough for Vision Representations

A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations. This focus has shaped both training objectives and evaluation protocols, implicitly treating global geometry as a proxy for representational competence. While global geometry effectively encodes which elements are present, it is often insensitive to how they are composed. We investigate this limitation by testing the ability of geometric metrics to predict compositional binding across a diverse suite of vision encoders. We find that standard geometry-based statistics exhibit near-zero correlation with compositional binding. In contrast, functional sensitivity, as measured by the input--output Jacobian, reliably tracks this capability. We further provide an analytic account showing that this disparity arises from objective design, as existing losses explicitly constrain embedding geometry but leave the local input--output mapping unconstrained. These results suggest that global embedding geometry captures only a partial view of representational competence and establish functional sensitivity as a critical complementary axis for modeling composite structure.

cs.CV↗

arXiv2026

Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors

Most existing 3D keypoint estimation methods rely on manual annotations or calibrated multi-view images, both of which are expensive to collect. This paper introduces KeyDiff3D, a framework that can accurately predict 3D keypoints from a single image, thus eliminating the need for such expensive data acquisitions. To achieve this, we leverage powerful geometric priors embedded in a pretrained multi-view diffusion model. In our framework, the diffusion model generates multi-view images from a single image, serving as supervision signals to provide 3D geometric cues to our model. We also introduce a 3D feature extractor that transforms implicit 3D priors embedded in the diffusion features into explicit 3D feature volumes. Beyond accurate keypoint estimation, we further introduce a pipeline that enables manipulation of 3D objects generated by the diffusion model. Experimental results on diverse datasets, including Human3.6M, CUB-200-2011, Stanford Dogs, and several in-the-wild and out-of-domain inputs, highlight the effectiveness of our method in terms of accuracy, generalization, and its ability to enable manipulation of 3D objects generated by the diffusion model from a single image.

cs.CV↗

arXiv2026

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretically realize a set of symbolic transition rules. We argue that equally important is error control, the dynamics governing hidden-state drift along the directions that distinguish symbolic states. We prove that affine recurrent networks, a class of models encompassing State-Space Models and Linear Attention, cannot correct errors along state-separating subspaces once they preserve state representations. Consequently, practical affine trackers do not learn robust state tracking; rather, they learn finite horizon solutions governed by accumulated state-relevant error. We characterize the mechanics of this failure, showing that tracking remains readable only while the accumulating within-class spread remains small relative to the initial between-class separation. We demonstrate empirically on group state-tracking tasks that this breakdown is predictable: tracking collapses when the distinguishability ratio crosses the readability threshold of the trained decoder. Across trained models, the point of this crossing predicts the horizon at which downstream accuracy fails. These results establish that robust state tracking is determined not only by an architecture's theoretical expressivity but crucially by its error control.

cs.LG↗

arXiv2026

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

Multimodal large language models (MLLMs) demonstrate strong video understanding by attending to visual tokens relevant to textual queries. To directly adapt this for localization in a training-free manner, we cast video reasoning segmentation as a video QA task and extract attention maps via rollout mechanism. However, raw attention maps are noisy and poorly aligned with object regions. We propose Decomposed Attention Fusion (DecAF), which refines these maps through two mechanisms: (1) contrastive object-background fusion and (2) complementary video-frame fusion. This method suppresses irrelevant activations and enhances object-focused cues, enabling direct conversion of attention maps into coarse segmentation masks. In addition, we introduce attention-guided SAM2 prompting for obtaining fine-grained masks. Unlike existing methods that jointly train MLLMs with SAM, our method operates entirely without retraining. DecAF outperforms training-free methods and achieves performance comparable to training-based methods on both referring and reasoning VOS benchmarks.

cs.CV↗

arXiv2026

GenOL: Generating Diverse Examples for Name-only Online Learning

Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate new concepts (e.g., classes), real-time manual annotation is impractical due to its costs and latency, which hinder real-time adaptation. To alleviate this, 'name-only' setup has been proposed, requiring only the name of concepts, not the supervised samples. A recent approach tackles this setup by supplementing data with web-scraped images, but such data often suffers from issues of data imbalance, noise, and copyright. To overcome the limitations of both human supervision and webly supervision, we propose GenOL using generative models for name-only training. But naive application of generative models results in limited diversity of generated data. Here, we enhance (i) intra-diversity, the diversity of images generated by a single model, by proposing a diverse prompt generation method that generates diverse text prompts for text-to-image models, and (ii) inter-diversity, the diversity of images generated by multiple generative models, by introducing an ensemble strategy that selects minimally overlapping samples. We empirically validate that the proposed \frameworkname outperforms prior arts, even a model trained with fully supervised data by large margins, in various tasks, including image recognition and multi-modal visual reasoning.

cs.LG↗

arXiv2026

Hierarchical Latent Action Model

Latent Action Models (LAMs) enable learning from actionless data for applications ranging from robotic control to interactive world models. However, existing LAMs typically focus on short-horizon frame transitions and capture low-level motion while overlooking longer-term temporal structure. In contrast, actionless videos often contain temporally extended and high-level skills. We present HiLAM, a hierarchical latent action model that discovers latent skills by modeling long-term temporal information. To capture these dependencies across long horizons, we utilize a pretrained LAM as a low-level extractor. This architecture aggregates latent action sequences, which contain the underlying dynamic patterns of the video, into high-level latent skills. Our experiments demonstrate that HiLAM improves over the baseline and exhibits robust dynamic skill discovery.

cs.RO↗

arXiv2025

CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy

Computational color constancy, or white balancing, is a key module in a camera's image signal processor (ISP) that corrects color casts from scene lighting. Because this operation occurs in the camera-specific raw color space, white balance algorithms must adapt to different cameras. This paper introduces a learning-based method for cross-camera color constancy that generalizes to new cameras without retraining. Our method leverages pre-calibrated color correction matrices (CCMs) available on ISPs that map the camera's raw color space to a standard space (e.g., CIE XYZ). Our method uses these CCMs to transform predefined illumination colors (i.e., along the Planckian locus) into the test camera's raw space. The mapped illuminants are encoded into a compact camera fingerprint embedding (CFE) that enables the network to adapt to unseen cameras. To prevent overfitting due to limited cameras and CCMs during training, we introduce a data augmentation technique that interpolates between cameras and their CCMs. Experimental results across multiple datasets and backbones show that our method achieves state-of-the-art cross-camera color constancy while remaining lightweight and relying only on data readily available in camera ISPs.

cs.CV↗

arXiv2025

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

Mimicry is a fundamental learning mechanism in humans, enabling individuals to learn new tasks by observing and imitating experts. However, applying this ability to robots presents significant challenges due to the inherent differences between human and robot embodiments in both their visual appearance and physical capabilities. While previous methods bridge this gap using cross-embodiment datasets with shared scenes and tasks, collecting such aligned data between humans and robots at scale is not trivial. In this paper, we propose UniSkill, a novel framework that learns embodiment-agnostic skill representations from large-scale cross-embodiment video data without any labels, enabling skills extracted from human video prompts to effectively transfer to robot policies trained only on robot data. Our experiments in both simulation and real-world environments show that our cross-embodiment skills successfully guide robots in selecting appropriate actions, even with unseen video prompts. The project website can be found at: https://kimhanjung.github.io/UniSkill.

cs.RO↗

arXiv2025

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models

We introduce Hierarchical Streaming Video Understanding, a task that combines online temporal action localization with free-form description generation. Given the scarcity of datasets with hierarchical and fine-grained temporal annotations, we demonstrate that LLMs can effectively group atomic actions into higher-level events, enriching existing datasets. We then propose OpenHOUSE (Open-ended Hierarchical Online Understanding System for Events), which extends streaming action perception beyond action classification. OpenHOUSE features a specialized streaming module that accurately detects boundaries between closely adjacent actions, nearly doubling the performance of direct extensions of existing methods. We envision the future of streaming action perception in the integration of powerful generative models, with OpenHOUSE representing a key step in that direction.

cs.CV↗

arXiv2025

Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images

360-degree visual content is widely shared on platforms such as YouTube and plays a central role in virtual reality, robotics, and autonomous navigation. However, consumer-grade dual-fisheye systems consistently yield imperfect panoramas due to inherent lens separation and angular distortions. In this work, we introduce a novel calibration framework that incorporates a dual-fisheye camera model into the 3D Gaussian splatting pipeline. Our approach not only simulates the realistic visual artifacts produced by dual-fisheye cameras but also enables the synthesis of seamlessly rendered 360-degree images. By jointly optimizing 3D Gaussian parameters alongside calibration variables that emulate lens gaps and angular distortions, our framework transforms imperfect omnidirectional inputs into flawless novel view synthesis. Extensive evaluations on real-world datasets confirm that our method produces seamless renderings-even from imperfect images-and outperforms existing 360-degree rendering models.

cs.CV↗

arXiv2025

Autoregressive Universal Video Segmentation Model

Recent video foundation models such as SAM2 excel at prompted video segmentation by treating masks as a general-purpose primitive. However, many real-world settings require unprompted segmentation that aims to detect and track all objects in a video without external cues, leaving today's landscape fragmented across task-specific models and pipelines. We recast streaming video segmentation as sequential mask prediction, analogous to language modeling, and introduce the Autoregressive Universal Segmentation Model (AUSM), a single architecture that unifies both prompted and unprompted video segmentation. Built on recent state-space models, AUSM maintains a fixed-size spatial state and scales to video streams of arbitrary length. Furthermore, all components of AUSM are designed for parallel training across frames, yielding substantial speedups over iterative training. On standard benchmarks (DAVIS17, YouTube-VOS 2018 & 2019, MOSE, YouTube-VIS 2019 & 2021, and OVIS) AUSM outperforms prior universal streaming video segmentation methods and achieves up to 2.5x faster training on 16-frame sequences.

cs.CV↗