arXiv subjects

Nels Numan

Publications and source records attributed to Nels Numan.

10 recordsLinked to original sources

arXiv2026

Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval

Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in recoverable observations rather than compressed latent state alone. We propose Visual Agentic Memory (VAM), a training-free framework with three components. Online Indexing supports selective evidence retention under streaming constraints. Hierarchical Memory organises retained evidence in a Parallel Representation that aligns temporal context with spatial observations. Agentic Retrieval searches, inspects, and verifies candidate evidence before producing a grounded answer. On OVO-Bench, VAM achieves the highest RT+BT average (68.41) across all reported baselines, improving over end-to-end use of the same underlying MLLM (Gemini 3 Flash, 67.46). On the month-scale split of MM-Lifelong train@month (105.6 hours over 51 days), VAM reaches 17.11%, second only to ReMA with GPT-5 (17.62%). These results suggest that long-horizon video understanding benefits from treating visual memory as an explicit, inspectable, and queryable substrate. Code is available at https://github.com/yiliu-li/Visual-Agentic-Memory.

cs.CV↗

arXiv2026

Semantic Reality: Interactive Context-Aware Visualization of Inter-Object Relationships in Augmented Reality

Bridging the physical and digital world through interaction remains a core challenge in augmented reality (AR). Existing systems target single objects, limiting support for planning, comparison, and assembly tasks that depend on relationships among multiple items. We present Semantic Reality, an AR system focused on surfacing inter-object connectivity and making it interactive. Leveraging multimodal reasoning, spatial anchoring, and physical action recognition, Semantic Reality maintains a persistent model of objects around the user and their relationships. Connections are visualized in-situ to highlight compatibility, reveal next steps, and reduce ambiguity during tasks. We contribute a connectivity-centered interaction paradigm and a system architecture that couples anchor tracking, action sensing, and model inference to construct a live connectivity graph. In an exploratory study comparing Semantic Reality to a single-object baseline, participants reported clearer inter-object understanding and higher engagement and satisfaction, without increased workload. A scenario study illustrates where connectivity aids planning, sequencing, and disambiguation.

cs.HC↗

arXiv2026

Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini

While large language models (LLMs) have accelerated 2D software development through intent-driven "vibe coding", prototyping intelligent Extended Reality (XR) experiences remains a major challenge. The fundamental barrier is not just the steep learning curve for human creators, but that low-level sensor APIs and complex game engine hierarchies are ill-suited for LLM reasoning, routinely exceeding context windows and inducing syntax hallucinations. To bridge this gap, we contribute XR Blocks, an open-source, LLM-native WebXR framework. Unlike traditional engines, XR Blocks introduces a semantic "Reality Model" that aligns spatial computing primitives (users, physical environments, and agents) with natural language, providing a robust, concise vocabulary optimized for generative AI. Building upon this foundation, we present Vibe Coding XR, an end-to-end prototyping workflow that leverages LLMs to translate high-level prompts (e.g., "create a dandelion that reacts to my hand") directly into functional, physics-aware mixed-reality applications. To minimize the friction of on-device testing, the workflow introduces a seamless desktop "simulated reality" to headset deployment loop. Finally, we introduce VCXR60, a pilot dataset of 60 XR prompts paired with an automated evaluation pipeline. Our technical evaluation demonstrates high one-shot execution success, enabling practitioners to bypass lowlevel hurdles and rapidly move from "idea to reality". Code and live demos are available at https://github.com/google/xrblocks and http://xrblocks.github.io/gem.

cs.HC↗

arXiv2025

XR Blocks: Accelerating Human-centered AI + XR Innovation

We are on the cusp where Artificial Intelligence (AI) and Extended Reality (XR) are converging to unlock new paradigms of interactive computing. However, a significant gap exists between the ecosystems of these two fields: while AI research and development is accelerated by mature frameworks like JAX and benchmarks like LMArena, prototyping novel AI-driven XR interactions remains a high-friction process, often requiring practitioners to manually integrate disparate, low-level systems for perception, rendering, and interaction. To bridge this gap, we present XR Blocks, a cross-platform framework designed to accelerate human-centered AI + XR innovation. XR Blocks strives to provide a modular architecture with plug-and-play components for core abstraction in AI + XR: user, world, peers; interface, context, and agents. Crucially, it is designed with the mission of "reducing frictions from idea to reality", thus accelerating rapid prototyping of AI + XR apps. Built upon accessible technologies (WebXR, three.js, TensorFlow, Gemini), our toolkit lowers the barrier to entry for XR creators. We demonstrate its utility through a set of open-source templates, samples, and advanced demos, empowering the community to quickly move from concept to interactive XR prototype. Site: https://xrblocks.github.io

cs.HC↗

arXiv2025

Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents

Proactive AR agents promise context-aware assistance, but their interactions often rely on explicit voice prompts or responses, which can be disruptive or socially awkward. We introduce Sensible Agent, a framework designed for unobtrusive interaction with these proactive agents. Sensible Agent dynamically adapts both "what" assistance to offer and, crucially, "how" to deliver it, based on real-time multimodal context sensing. Informed by an expert workshop (n=12) and a data annotation study (n=40), the framework leverages egocentric cameras, multimodal sensing, and Large Multimodal Models (LMMs) to infer context and suggest appropriate actions delivered via minimally intrusive interaction modes. We demonstrate our prototype on an XR headset through a user study (n=10) in both AR and VR scenarios. Results indicate that Sensible Agent significantly reduces perceived interaction effort compared to voice-prompted baseline, while maintaining high usability and achieving higher preference.

cs.HC↗

arXiv2025

AdjustAR: AI-Driven In-Situ Adjustment of Site-Specific Augmented Reality Content

Site-specific outdoor AR experiences are typically authored using static 3D models, but are deployed in physical environments that change over time. As a result, virtual content may become misaligned with its intended real-world referents, degrading user experience and compromising contextual interpretation. We present AdjustAR, a system that supports in-situ correction of AR content in dynamic environments using multimodal large language models (MLLMs). Given a composite image comprising the originally authored view and the current live user view from the same perspective, an MLLM detects contextual misalignments and proposes revised 2D placements for affected AR elements. These corrections are backprojected into 3D space to update the scene at runtime. By leveraging MLLMs for visual-semantic reasoning, this approach enables automated runtime corrections to maintain alignment with the authored intent as real-world target environments evolve.

cs.HC↗

arXiv2025

Decoupled Hands: An Approach for Aligning Perspectives in Collaborative Mixed Reality

When collaborating relative to a shared 3D virtual object in mixed reality (MR), users may experience communication issues arising from differences in perspective. These issues include occlusion (e.g., one user not being able to see what the other is referring to) and inefficient spatial references (e.g., "to the left of this" may be confusing when users are positioned opposite to each other). This paper presents a novel technique for automatic perspective alignment in collaborative MR involving co-located interaction centered around a shared virtual object. To align one user's perspective on the object with a collaborator's, a local copy of the object and any other virtual elements that reference it (e.g., the collaborator's hands) are dynamically transformed. The technique does not require virtual travel and preserves face-to-face interaction. We created a prototype application to demonstrate our technique and present an evaluation methodology for related MR collaboration and perspective alignment scenarios.

cs.HC↗

arXiv2025

CoCreatAR: Enhancing Authoring of Outdoor Augmented Reality Experiences Through Asymmetric Collaboration

Authoring site-specific outdoor augmented reality (AR) experiences requires a nuanced understanding of real-world context to create immersive and relevant content. Existing ex-situ authoring tools typically rely on static 3D models to represent spatial information. However, in our formative study (n=25), we identified key limitations of this approach: models are often outdated, incomplete, or insufficient for capturing critical factors such as safety considerations, user flow, and dynamic environmental changes. These issues necessitate frequent on-site visits and additional iterations, making the authoring process more time-consuming and resource-intensive. To mitigate these challenges, we introduce CoCreatAR, an asymmetric collaborative mixed reality authoring system that integrates the flexibility of ex-situ workflows with the immediate contextual awareness of in-situ authoring. We conducted an exploratory study (n=32) comparing CoCreatAR to an asynchronous workflow baseline, finding that it enhances engagement, creativity, and confidence in the authored output while also providing preliminary insights into its impact on task load. We conclude by discussing the implications of our findings for integrating real-world context into site-specific AR authoring systems.

cs.HC↗

arXiv2024

BlendScape: Enabling End-User Customization of Video-Conferencing Environments through Generative AI

Today's video-conferencing tools support a rich range of professional and social activities, but their generic meeting environments cannot be dynamically adapted to align with distributed collaborators' needs. To enable end-user customization, we developed BlendScape, a rendering and composition system for video-conferencing participants to tailor environments to their meeting context by leveraging AI image generation techniques. BlendScape supports flexible representations of task spaces by blending users' physical or digital backgrounds into unified environments and implements multimodal interaction techniques to steer the generation. Through an exploratory study with 15 end-users, we investigated whether and how they would find value in using generative AI to customize video-conferencing environments. Participants envisioned using a system like BlendScape to facilitate collaborative activities in the future, but required further controls to mitigate distracting or unrealistic visual elements. We implemented scenarios to demonstrate BlendScape's expressiveness for supporting environment design strategies from prior work and propose composition techniques to improve the quality of environments.

cs.HC↗

arXiv2024

SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending

There is increased interest in using generative AI to create 3D spaces for Virtual Reality (VR) applications. However, today's models produce artificial environments, falling short of supporting collaborative tasks that benefit from incorporating the user's physical context. To generate environments that support VR telepresence, we introduce SpaceBlender, a novel pipeline that utilizes generative AI techniques to blend users' physical surroundings into unified virtual spaces. This pipeline transforms user-provided 2D images into context-rich 3D environments through an iterative process consisting of depth estimation, mesh alignment, and diffusion-based space completion guided by geometric priors and adaptive text prompts. In a preliminary within-subjects study, where 20 participants performed a collaborative VR affinity diagramming task in pairs, we compared SpaceBlender with a generic virtual environment and a state-of-the-art scene generation framework, evaluating its ability to create virtual spaces suitable for collaboration. Participants appreciated the enhanced familiarity and context provided by SpaceBlender but also noted complexities in the generative environments that could detract from task focus. Drawing on participant feedback, we propose directions for improving the pipeline and discuss the value and design of blended spaces for different scenarios.

cs.AI↗