arXiv subjects

Yuxuan Weng

Publications and source records attributed to Yuxuan Weng.

4 recordsLinked to original sources

arXiv2026

NephoCodex: Exploring Bounded Material Agency in Weather Data Physicalization

Weather is a complex, continuously changing system in which uncertainty is intrinsic. Physicalizing this uncertainty introduces further variation because computational outputs cannot fully determine material behavior. We distinguish computational uncertainty from material variability and introduce bounded material agency: computation constrains material realization without fixing its exact appearance. We present NephoCodex, a data physicalization system informed by a formative study that constructs five artistic weather states and predicts probability distributions over them. Probability-weighted mappings translate these distributions into material control proposals, while entropy-based regulation, local sensing, and safety constraints bound their execution through mist, airflow, light, and transparent displays. A within-participant study found increased spatial presence and physical demand, while perceived data comprehensibility remained inconclusive after correction. These findings contribute to hybrid data physicalization by showing how variable material expression can be paired with stable digital annotations and how embodied experience can be evaluated separately from data comprehension.

cs.HC↗

arXiv2026

The Garden of Forking Paths: Threading Narrative Archetype as a Semantic Signal Through Gameplay Planning

Generative models can produce individual game facets, but whole-game generation remains an orchestration problem: narrative, level structure, encounters, objectives, rewards, and visuals must express shared intent. We present Forking Garden, a branching game generation system that uses narrative archetype as a persistent semantic signal across the generation pipeline. Narrative progression is represented as soft Rise/Fall states; candidate plot nodes are generated before structural constraints assemble archetype-conforming graphs. The same state then conditions encounter composition, objectives, rewards, and runtime difficulty adaptation, while a shared symbolic schema preserves narrative entities and gameplay configurations through content instantiation. Across 10 storylines, generated paths exhibit distinguishable archetypal trajectories, narrative threat predicts damage taken by a threat-blind combat agent, and generate-first-constrain-later yields 2.6 times the entity diversity of a hierarchical baseline. A 16-participant study further suggests that propagated Rise/Fall distinctions can remain meaningful during play, while also supporting narrative understanding and creator-oriented interpretation.

cs.HC↗

arXiv2026

VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals

Wearable devices enable continuous health monitoring from multimodal signals, but real-world deployment is hindered by limited labeled data and pervasive sensor incompleteness. While large-scale self-supervised pretraining reduces label dependence, most existing methods assume full modality availability. Current approaches for handling modality missingness often reconstruct entire absent signals, which can encourage hallucinating modality-specific details that are not inferable from the observed sensor signals and degrade robustness. We propose VCR, a self-supervised framework that learns to extract valid representations robust to modality missingness. VCR employs an orthogonal tokenizer to enforce strict orthogonal disentanglement by rectifying latent manifolds and applying a geometric projection, separating each modality into shared semantics and modality-specific residuals. This design preserves complete information integrity while serving as a structural foundation for robust learning under modality missingness. The resulting tokens are processed by a missing-aware mixture-of-experts backbone that adapts to varying patterns of modality availability. By constraining the objective to reconstruct only the shared components of missing modalities, VCR effectively mitigates hallucinations of non-inferable modality-specific details. Across multiple health monitoring tasks, VCR consistently improves performance and robustness under full, single-missing, and multiple-missing modality settings compared with strong supervised and self-supervised baselines.

cs.LG↗

arXiv2024

Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution for applications unamenable to techniques requiring computer visions. However, the scarcity of labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough of foundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi's generalizability across various environments.

cs.CV↗