CLChen Liang

Chen Liang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Chen Liang has a total of 122 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SilkSense: A Craft-Inspired Fabrication Method for Silk-based Functional Interfaces

    by Yixiong Wang, Yan Li, Yuxiao Huang, Wenyu Wang, Chen Liang

    While silk is attractive for on-body sensing due to its biocompatibility and skin affinity, its smooth fiber surface and limited capillary absorption make it poorly suited to existing fabrication methods based on liquid infiltration and mechanical anchoring. Inspired by Gambiered Canton Gauze (Xiangyunsha), a traditional craft with a centuries-long history of silk surface modification, we present SilkSense, a fabric-level workflow for functionalizing commercially available silk. By analyzing the craft’s core processing stages and identifying the underlying interfacial mechanisms, we organize the responsible material components into a two-stage workflow: Dioscorea cirrhosa polyphenol pretreatment followed by Fe-HA/FA and PEDOT: PSS composite coating. The resulting fabric supports mask-based patterning (up to 1.5 mm resolution) and freehand painting and exhibits wash durability (approximately 15.6% resistance drift after 20 high-intensity cycles) under our test conditions. SilkSense fabric enables three on-body input modalities, including pressing, bending, and pinching, whose sensing characteristics can be translated into wearable interface designs across different body locations, validated through a drone control demonstration in which subtle single-hand finger movements drive three-channel real-time closed-loop interaction. Together, these results show how craft-derived interfacial principles can support patternable, maintainable, and multimodal silk-based interaction surfaces.

  • DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer

    by Hengye Lyu, Zisu Li, Yue Hong, Yueting Weng, Jiaxin Shi, Hanwang Zhang, Chen Liang

  • Open Access

    Machine Civilization: Exploring Machine Alterity through a Generative Semiotic Installation 35

    by Jia-Qi Shi, Yixiong Wang, Jiawen Zheng, Hourun Wang, Yufeng Zeng, Chen Liang

    Machine Civilization is a multi-screen mechanical installation that imagines an autonomous system observing the world through diverse machine perspectives and generating scripts independent of human semantic frameworks. The installation implements a real-time system of observation, interpretation, collective deliberation, and script inscription, producing formal familiarity and semantic untranslatability. Taking this artwork as a case, this study starts from machines’ autonomous cognitive features and takes “machine writing” as its entry point to explore three issues in the intelligence era: the gap between interpretability and understandability, the flow of meaning between humans and machines, and the ethical encounter with the machine as the Other. Inspired by Levinas’s concept of alterity, the work challenges anthropocentric perspectives by emphasizing machine cognition’s autonomy beyond human semantics. This study contributes to expanding the epistemological and ethical discussion on non-human intelligence through artistic practice, and exploring more open modes of interaction with the technological Other.

  • Open Access

    Is it Dark? Understanding Dark Pattern Influence through User Behavioral Strategies and Interpretations in Livestream E-commerce

    by Yue Qin, Tengjia Zuo, Chen Liang

    Dark patterns are commonly defined as manipulative interface designs that undermine user autonomy, with prior work evaluating their impact through predefined negative framings. However, users’ lived experiences of influential design are often more heterogeneous and situational. This paper examines how users experience and interpret expert-defined dark pattern elements in Chinese livestream e-commerce. We conducted a qualitative study using video-stimulated recall interviews based on participants’ screen recordings (N=17), capturing real behaviors and in-situ reasoning. Our findings show that user responses extend beyond a simple compliance–resistance dichotomy, unfolding through a set of behavioral strategies, composite attributional reasoning, and diverse interpretations of influence. While some designs were perceived as coercive or deceptive, others were experienced as rational persuasion. We contribute a user-centered behavioral taxonomy and a model of design influence grounded in three experiential dimensions, offering insights into how influence is interpreted in dynamic, real-world interaction contexts.


  • Open Access

    SituFont: A Just-in-Time Adaptive Intervention Interface for Enhancing Mobile Readability in Situational Visual Impairments

    by Jingruo Chen, Kexin Nie, Mingshan Zhang, Chun Yu, Zhiqi Gao, Kun Yue, Yuanchun Shi, Chen Liang

    Situational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobile readability by dynamically adjusting font parameters based on real-time contextual changes. Using smartphone sensors and a human-in-the-loop approach, SituFont personalizes text presentation to accommodate personal factors (e.g., fatigue, distraction) and environmental conditions (e.g., lighting, motion, location). To inform its design, we conducted formative interviews (N=15) to identify key SVI factors and controlled experiments (N=18) to quantify their impact on optimal text parameters. A comparative user study (N=12) across eight simulated SVI scenarios demonstrated SituFont’s effectiveness in improving smartphone mobile readability in terms of improved efficiency and reduced workload compared with a non-trivial manual adjustment baseline.


  • Open Access

    ARtisanAI: An AR and AI-Enhanced Experience for Ceramic Design-to-Craft

    by Zijun Wan, Yuxuan Guo, Haowei Xiong, Kexin Nie, Chen Liang

    Novice ceramic makers often struggle to bridge early-stage inspiration with feasible physical making, particularly when transitioning from ideation to embodied shaping and surface decoration. To address this challenge, we present ARtisanAI, an integrated AI and AR workflow that supports the full ceramic design-to-craft process across three stages: ideation, shaping, and decoration. We implement ARtisanAI as a functional prototype that enables users to generate inspectable 3D references from hand-drawn sketches and receive in-situ AR scaffolding throughout the making process. In a mixed-methods user study (N=16), questionnaire responses and semi-structured interviews reveal stage-dependent complementarity between the two technologies: AI proved most beneficial for expanding the design space during ideation, while AR was most effective for supporting shaping consistency in situ. Participants further identified opportunities to enhance color planning and glazing guidance in future iterations.


  • Open Access

    PerforMagic: Coordinating Bodily Performance and Camera Movement in AI Video Creation

    by Yufeng Zeng, Troy TianYu Lin, Shuyue Li, Yue Hong, Anca-Simona Horvath, Chen Liang

    Performance-driven AI video creation allows users to express ideas through bodily action, but it also requires performers to coordinate embodied performance with camera movement. For solo creators, managing this coordination in real time can be cognitively demanding and limits cinematic exploration. We present PerforMagic, an interactive system that explores how coordination between performance and camera movement can be supported through a re-filming interaction. Users first record their performance without explicitly controlling the camera. The system then reconstructs the performance in a virtual environment, enabling users to reason about and explore camera movements in relation to their embodied actions. Through a user study, participants reported clearer relationships between performance and camera movement, less pressure during performance, and broader exploration of camera techniques. Our work contributes an interaction concept for coordinating embodied action and cinematography in performance-driven AI video creation and offers qualitative insights into how staged interaction supports expressive control.

  • Open Access

    RealTwin: Concept Graph Representation and Grounding Framework for Reality-Preserving Digital Twin Reconstruction

    by Zisu Li, Ruohao Li, Jiawei Li, Chao Liu, Junyi Zhu, Daniela Rus, Chen Liang, Mingming Fan


  • Open Access

    Learning Brain Representation with Hierarchical Visual Embeddings

    by Jiawen Zheng, Haonan Jia, Ming Li, Yuhui Zheng, Yufeng Zeng, Yang Gao, Chen Liang

    Decoding visual representations from brain signals has attracted significant attention in both neuroscience and artificial intelligence. However, the degree to which brain signals truly encode visual information remains unclear. Current visual decoding approaches explore various brain-image alignment strategies, yet most emphasize high-level semantic features while neglecting pixel-level details, thereby limiting our understanding of the human visual system. In this paper, we propose a brain-image alignment strategy that leverages multiple pre-trained visual encoders with distinct inductive biases to capture hierarchical and multi-scale visual representations, while employing a contrastive learning objective to achieve effective alignment between brain signals and visual embeddings. Furthermore, we introduce a Fusion Prior, which learns a stable mapping on large-scale visual data and subsequently matches brain features to this pre-trained prior, thereby enhancing distributional consistency across modalities. Extensive quantitative and qualitative experiments demonstrate that our method achieves a favorable balance between retrieval accuracy and reconstruction fidelity.