arXiv subjects

Zixiong Su

Publications and source records attributed to Zixiong Su.

4 recordsLinked to original sources

arXiv2026

Towards Interactive Intelligence for Digital Humans

We introduce Interactive Intelligence, a novel paradigm of digital human that is capable of personality-aligned expression, adaptive interaction, and self-evolution. To realize this, we present Mio (Multimodal Interactive Omni-Avatar), an end-to-end framework composed of five specialized modules: Thinker, Talker, Face Animator, Body Animator, and Renderer. This unified architecture integrates cognitive reasoning with real-time multimodal embodiment to enable fluid, consistent interaction. Furthermore, we establish a new benchmark to rigorously evaluate the capabilities of interactive intelligence. Extensive experiments demonstrate that our framework achieves superior performance compared to state-of-the-art methods across all evaluated dimensions. Together, these contributions move digital humans beyond superficial imitation toward intelligent interaction.

cs.CV↗

arXiv2026

OpticalAging: Real-time Presbyopia Simulation for Inclusive Design via Tunable Lenses

Presbyopia, a common age-related vision condition affecting most people as they age, often remains inadequately understood by those unaffected. To help bridge the gap between abstract accessibility knowledge and a more grounded appreciation of perceptual challenges, this study presents OpticalAging, an optical see-through simulation approach. Unlike VR-based methods, OpticalAging uses dynamically controlled tunable lenses to simulate the first-person visual perspective of presbyopia's distance-dependent blur during real-world interaction, aiming to enhance awareness. While acknowledging critiques regarding simulation's limitations in fully capturing lived experience, we position this tool as a complement to user-centered methods. Our user study (N = 19, 18-35 years old) provides validation: quantitative measurements show statistically significant changes in near points across three age modes (40s, 50s, 60s), while qualitative results suggest increases in self-reported understanding and awareness of perceptual challenges among participants. The integration of our tool into a design task showcases its potential applicability within age-inclusive design workflows when used critically alongside direct user engagement.

cs.HC↗

arXiv2026

A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation

Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods continue to suffer from residual interference in complex acoustic scenes. This performance limitation stems largely from a data bottleneck: in-the-wild datasets contain weak labels and severe co-occurrence of events. These flaws induce models to learn spurious correlations between background noise and target categories instead of robust acoustic features. To address this, we propose an automated pipeline that eliminates co-occurrence of events by mining high-purity single-event segments from in-the-wild datasets via a semantically consistent synthesis protocol. Utilizing this pipeline, we constructed Hive, a high-quality synthetic dataset comprising 2.4k hours of raw audio. Experimental results demonstrate that, compared with the state-of-the-art model SAM-Audio which was trained on a huge dataset $\sim$500 times larger than Hive, certain open-source models trained on Hive achieve competitive separation accuracy and perceptual quality. Moreover, these models exhibited remarkable zero-shot generalization on out-of-distribution evaluation benchmarks. These findings highlight that prioritizing purity of supervised signals enables significant data efficiency, offering a new paradigm for training robust auditory foundation models with reduced computational costs. Code and dataset are available at https://cslikai.cn/Hive.

cs.SD↗

arXiv2023

LipLearner: Customizable Silent Speech Interactions on Mobile Devices

Silent speech interface is a promising technology that enables private communications in natural language. However, previous approaches only support a small and inflexible vocabulary, which leads to limited expressiveness. We leverage contrastive learning to learn efficient lipreading representations, enabling few-shot command customization with minimal user effort. Our model exhibits high robustness to different lighting, posture, and gesture conditions on an in-the-wild dataset. For 25-command classification, an F1-score of 0.8947 is achievable only using one shot, and its performance can be further boosted by adaptively learning from more data. This generalizability allowed us to develop a mobile silent speech interface empowered with on-device fine-tuning and visual keyword spotting. A user study demonstrated that with LipLearner, users could define their own commands with high reliability guaranteed by an online incremental learning scheme. Subjective feedback indicated that our system provides essential functionalities for customizable silent speech interactions with high usability and learnability.

cs.HC↗