arXiv subjects
Publications and source records attributed to Zhiming Liu.
We introduce a new branching bisimulation for probabilistic processes, which induces a more refined equivalence relation than any known equivalence that abstracts from unobservable actions, with a rooted version that is a congruence for a language of probabilistic process with the usual static as well as dynamic constructs including recursion.
A range of methods aim to enhance the performance of vision-language models (VLMs) at test time. Among them, transduction has emerged as a promising paradigm due to its strong compatibility and efficiency. However, realistic evaluations often involve highly imbalanced class distributions, which cause performance degradation or even collapse. In this work, we systematically revisit transduction from the perspective of penalized likelihood estimation (PLE), showing that PLE with a KL-divergence anchor term naturally yields an adaptive shrinkage behavior between prior anchors and empirical estimates. From this viewpoint, the brittleness of transductive methods can be attributed to the absence of anchoring mechanism and static modeling of the shrinkage strength. Therefore, we propose Mixture of Von Mises-Fisher Models with Dynamic Shrinkage (MOON). MOON is built upon a mixture of von Mises-Fisher distributions to model feature representations on the unit hypersphere. To handle imbalance, MOON dynamically adjusts the shrinkage strength using zero-shot priors at both instance and class levels. Thus, it suppresses unreliable assignments and prevents harmful updates from outlier classes, thereby mitigating negative transfer. MOON is model-agnostic, training-free, and requires no task-specific hyperparameter tuning. Extensive experiments further validate the advantage of MOON in both performance and efficiency. Our code is available at https://github.com/walawalagoose/MOON
Vision-Language Models (VLMs) such as CLIP have become a standard backbone for open-vocabulary recognition, yet their zero-shot predictions remain vulnerable to distribution shifts encountered at deployment. Test-Time Adaptation (TTA) has recently been extended to CLIP as a lightweight solution, leading to a rapidly growing body of TTA4CLIP methods. However, empirical progress in this area has largely outpaced our understanding of what truly drives adaptation, where their gains originate, and under which shifts they remain reliable. In this paper, we take a step back from the pursuit of state-of-the-art accuracy and conduct a systematic controlled study of TTA4CLIP. We first organize existing methods into three unified paradigms according to what is updated at test time. We then introduce TTABC, an open-source TTA Benchmark for CLIP, which standardizes evaluation protocols and integrates more than 20 representative methods. Our controlled empirical analysis focuses on three key areas. First, we determine the driving factors in parameter-based methods, revealing that adaptation gains are primarily driven by test-time evidence and reliable proxies rather than heavy optimization. Second, we explore evidence utilization beyond heavy parameter tuning, showing that competitive and efficient performance can be achieved through cross- or current-sample evidence and lightweight prototype updates. Finally, we demonstrate that there is no silver bullet for TTA: no single adaptation paradigm is universally optimal, and the preferred paradigm depends on the nature of shift. We hope our benchmark and study provide a clearer understanding of the current TTA4CLIP landscape and establish a foundation for further research.
High-quality cardiopulmonary resuscitation (CPR) requires stable control of compression rhythm and depth, yet most training systems presuppose instructor mediation, repeated practice, and explanatory guidance-assumptions that do not hold in the Tibet Autonomous Region, where instruction is fragmented and learners' linguistic and educational backgrounds are heterogeneous. We present TibetCPR, a low-cost, self-guided CPR training system that pairs depth-driven electrotactile feedback with rhythm-driven visual cues within a Tibetan-language narrative. In a randomised study with 40 lay community members aged 19--56, the experimental group showed progressive minute-by-minute stabilisation of rhythm and depth across a 10-minute intervention, substantially exceeding an unguided-practice control, with gains transferring to an unscaffolded one-minute post-test. Qualitative accounts described the feedback as legible through participants' bodily action, and usability was high (SUS = 84.3). We synthesise three transferable design principles for self-guided embodied training: feedback as a calibration reference, not an immediate corrector; modality temporal granularity matched to behaviour's temporal structure; and autonomous interpretability as a deployment prerequisite, not an after-effect of usability.
Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood. In this work, we reveal that hallucinations are strongly associated with a human-like attention distraction phenomenon, where humans under divided focus experience degraded visual clarity and produce inaccurate descriptions, while in models the same mechanism manifests as spatial inconsistency in multi-head attention and temporal fading of attention to image tokens during decoding. We further provide theoretical insights that attention dispersion increases model complexity and degrades classification generalization. Motivated by these findings, we propose an Attention-Focused Approach for Improved Image Perception (AFIP), which corrects attention distraction via cross-head attention enrichment and reinforces visual grounding through dynamic historical attention enhancement. Extensive experiments on multiple benchmarks and models validate the effectiveness of AFIP without additional training. Code is available at: https://github.com/MIKUZ12/AFIP.
Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer, 3D architectures and require multi-frame input, but their large computational cost and memory usage limit real-time deployment, especially in resource-constrained scenarios. In this work, we propose ReMATF, a lightweight recurrent framework that restores videos using only two frames at a time while preserving spatial detail and temporal stability. ReMATF combines a multi-scale encoder-decoder with temporal warping and a motion-adaptive temporal fusion module that performs per-pixel fusion between the warped previous output and the current prediction to enhance coherence without enlarging the temporal window. This design reduces flicker, sharpens details, and remains efficient. Experiments on synthetic and real turbulence datasets show consistent improvements in PSNR/SSIM and perceptual quality (LPIPS), along with substantially faster inference than multi-frame transformer baselines, making ReMATF suitable turbulence mitigation in resource-constrained scenarios.
Current VLMs have demonstrated capabilities across a wide range of multimodal tasks. Typically, in a pretrained VLM, all layers are engaged by default to make predictions on downstream tasks. We find that intervening on a single layer, such as by zeroing its parameters, can improve the performance on certain tasks, indicating that some layers hinder rather than help downstream tasks. We systematically investigate how individual layers influence different tasks via layer intervention. Specifically, we measure the change in performance relative to the base model after intervening on each layer and observe improvements when bypassing specific layers. This improvement can be generalizable across models and datasets, indicating the presence of Task-Interfering Layers that harm downstream tasks' performance. We introduce Task-Layer Interaction Vector, which quantifies the effect of intervening on each layer of a VLM given a task. These task-interfering layers exhibit task-specific sensitivity patterns: tasks requiring similar capabilities show consistent response trends under layer interventions, as evidenced by the high similarity in their task-layer interaction vectors. Inspired by these findings, we propose TaLo (Task-Adaptive Layer Knockout), a training-free, test-time adaptation method that dynamically identifies and bypasses the most interfering layer for a given task. Without parameter updates, TaLo improves performance across various models and datasets, including boosting Qwen-VL's accuracy on the Maps task in ScienceQA by up to 16.6%. Our work reveals an unexpected form of modularity in pretrained VLMs and provides a plug-and-play, training-free mechanism to unlock hidden capabilities at inference time. The source code will be publicly available.
In this paper, we systematically investigate the connection between linearizable objects and forward simulation. We prove that the sets of linearizable objects satisfying wait-freedom (resp., lock-freedom or obstruction-freedom) form a bounded join-semilattice under the forward simulation relation, and that the sets of linearizable objects without liveness constraints form a bounded lattice under the same relation. Thus, forward simulation is not only a proof technique for linearizability but also induces an algebraic hierarchy of linearizable objects. As part of our lattice result, we propose an equivalent characterization of linearizability by reducing checking linearizability w.r.t. sequential specification $Spec$ into checking forward simulation w.r.t. an object $\mathcal{U}_{Spec}$.
Multi-view multi-label learning frequently suffers from simultaneous feature absence and incomplete annotations, due to challenges in data acquisition and cost-intensive supervision. To tackle the complex yet highly practical problem while overcoming the existing limitations of feature recovery, representation disentanglement, and label semantics modeling, we propose an Adaptive Disentangled Representation Learning method (ADRL). ADRL achieves robust view completion by propagating feature-level affinity across modalities with neighborhood awareness, and reinforces reconstruction effectiveness by leveraging a stochastic masking strategy. Through disseminating category-level association across label distributions, ADRL refines distribution parameters for capturing interdependent label prototypes. Besides, we formulate a mutual-information-based objective to promote consistency among shared representations and suppress information overlap between view-specific representation and other modalities. Theoretically, we derive the tractable bounds to train the dual-channel network. Moreover, ADRL performs prototype-specific feature selection by enabling independent interactions between label embeddings and view representations, accompanied by the generation of pseudo-labels for each category. The structural characteristics of the pseudo-label space are then exploited to guide a discriminative trade-off during view fusion. Finally, extensive experiments on public datasets and real-world applications demonstrate the superior performance of ADRL.
This study investigates the evolving attitudes of philosophy scholars towards the participation of generative AI based Intelligent User Interfaces (IUIs) in philosophical discourse. We conducted a three year (2023--2025) mixed methods longitudinal study with 16 philosophy scholars and students. Qualitative data from annual interviews reveal a three stage evolution in attitude: from initial resistance and unfamiliarity, to instrumental acceptance of the IUI as a tool, and finally to a deep principled questioning of the IUI's fundamental capacity for genuine philosophical thought. Quantitative data from blind assessments, where participants rated anonymized philosophical answers from both humans and an IUI, complement these findings. While participants acknowledged the IUI's proficiency in tasks requiring formal logic and knowledge reproduction, they consistently identified significant shortcomings in areas demanding dialectical reasoning, originality and embodied understanding. The study concludes that participants do not see the IUI as a peer but rather as a sophisticated mirror whose capabilities and limitations provoke a deeper reflection on the unique and irreplaceable human dimensions of philosophical inquiry, such as intuition, value laden commitment and the courage to question fundamental premises.
This study explores the design of Intelligent User Interfaces (IUIs) to address the profound existential loneliness of terminally ill individuals. While Human-Computer Interaction (HCI) has made inroads in "Thanatechnology," current research often focuses on practical aspects like digital legacy management, overlooking the subjective, existential needs of those facing death in isolation. To address this gap, we conducted in-depth qualitative interviews with 14 lonely, terminally ill individuals. Our core contributions are: (1) An empirically-grounded model articulating the complex psychological, practical, social, and spiritual needs of this group; (2) The "Three Pillars, Twelve Principles" framework for designing IUIs as "Existential Companions"; and (3) A critical design directive derived from user evaluations: technology in this context should aim for transcendence over simulation. The findings suggest that IUIs should create experiences that augment or surpass human capabilities, rather than attempting to simulate basic human connections, which can paradoxically deepen loneliness. This research provides a clear, user-centered path for designing technology that serves not as a "tool for dying," but as a "partner for living fully until the end".
Over the past decade, specialized social networking applications have become a cornerstone of life for many gay men in China. This paper employs a longitudinal mixed-methods approach to investigate how Chinese men who have sex with men (MSM) have shifted their attitudes toward these platforms between approximately 2013 and 2023. Drawing on archival analysis of online discourses, a quantitative survey of 412 participants, and in-depth semi-structured interviews with 32 participants, we trace the complex trajectory of this evolution. Our findings reveal a clear pattern: from the initial embrace of these applications as revolutionary tools for community building and identity affirmation (2014--2017), to a period of growing ambivalence and critique centered on commercialization, ``hookup culture,'' and multiple forms of discrimination (2017--2020), and finally to the present era (2020--2023), characterized by pragmatic, fragmented, yet simultaneously critical and reconstructive uses. Today, users strategically employ a repertoire of applications -- including global platforms (e.g., Grindr and Tinder), domestic mainstream platforms (e.g., Blued), and niche alternatives (e.g., Aloha) -- to fulfill differentiated needs. We develop a detailed temporal framework to capture this attitudinal evolution and discuss its design implications for creating more supportive, secure, and community-oriented digital environments for marginalized groups.
Type 2 diabetes patients in China face many significant challenges in patient-provider communication and self management In light of this, this work designed,implemented,and evaluated an AI-driven, personalized, multi-functional mobile app system named T2MD Health. The appintegrates real-time patient- provider conversation transcription,medical terminology interpretation, daily health tracking, and adata-driven feedback loop. We conducted qualitative interviewswith 40 participants to study key user needs before systemdevelopment and a mixed- method controlled experiment with 60participants after to evaluate the effectiveness and usability ofthe app. Evaluation results showed that the app was effective inimproving patient-provider communication efficiency, patientunderstanding and knowledge retention,and patient selfmanagement, Patient feedback also revealed that the app has thepotential to address the urban-rural gap in the access to medica!consultation services to some extent, Findings ofthis study couldinform future studies that seek to utilize mobile apps andartificial intelligence to support patients with chronic diseases.
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we propose BadThink, the first backdoor attack designed to deliberately induce "overthinking" behavior in CoT-enabled LLMs while ensuring stealth. When activated by carefully crafted trigger prompts, BadThink manipulates the model to generate inflated reasoning traces - producing unnecessarily redundant thought processes while preserving the consistency of final outputs. This subtle attack vector creates a covert form of performance degradation that significantly increases computational costs and inference time while remaining difficult to detect through conventional output evaluation methods. We implement this attack through a sophisticated poisoning-based fine-tuning strategy, employing a novel LLM-based iterative optimization process to embed the behavior by generating highly naturalistic poisoned data. Our experiments on multiple state-of-the-art models and reasoning tasks show that BadThink consistently increases reasoning trace lengths - achieving an over 17x increase on the MATH-500 dataset - while remaining stealthy and robust. This work reveals a critical, previously unexplored vulnerability where reasoning efficiency can be covertly manipulated, demonstrating a new class of sophisticated attacks against CoT-enabled systems.
Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. Current state-of-the-art methods are based on transformer and 3D architectures and require multi-frame input, but their large computational cost and memory usage limit real-time deployment, especially in resource-constrained scenarios. In this work, we propose RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator, designed for efficient and temporally consistent video restoration under AT conditions. RMFAT adopts a lightweight recurrent framework that restores each frame using only two inputs at a time, significantly reducing temporal window size and computational burden. It further integrates multi-scale feature encoding and decoding with temporal warping modules at both encoder and decoder stages to enhance spatial detail and temporal coherence. Extensive experiments on synthetic and real-world atmospheric turbulence datasets demonstrate that RMFAT not only outperforms existing methods in terms of clarity restoration (with nearly a 9\% improvement in SSIM) but also achieves significantly improved inference speed (more than a fourfold reduction in runtime), making it particularly suitable for real-time atmospheric turbulence suppression tasks.
Reliability prediction is crucial for ensuring the safety and security of software systems, especially in the context of industry practices. While various metrics and measurements are employed to assess software reliability, the complexity of modern systems necessitates a deeper understanding of how these metrics interact with security and safety concerns. This paper explores the interplay between software reliability, safety, and security, offering a comprehensive analysis of key metrics and measurement techniques used in the industry for reliability prediction. We identify critical threats to software reliability and provide a threat estimation framework that incorporates both safety and security aspects. Our findings suggest that integrating reliability metrics with safety and security considerations can enhance the robustness of software systems. Furthermore, we propose a set of actionable guidelines for practitioners to improve their reliability prediction models while simultaneously addressing the security and safety challenges of contemporary software applications.
Atmospheric turbulence (AT) introduces severe degradations, such as rippling, blur, and intensity fluctuations, that hinder both image quality and downstream vision tasks like target detection. While recent deep learning-based approaches have advanced AT mitigation using transformer and Mamba architectures, their high complexity and computational cost make them unsuitable for real-time applications, especially in resource-constrained settings such as remote surveillance. Moreover, the common practice of separating turbulence mitigation and object detection leads to inefficiencies and suboptimal performance. To address these challenges, we propose JDATT, a Joint Distillation framework for Atmospheric Turbulence mitigation and Target detection. JDATT integrates state-of-the-art AT mitigation and detection modules and introduces a unified knowledge distillation strategy that compresses both components while minimizing performance loss. We employ a hybrid distillation scheme: feature-level distillation via Channel-Wise Distillation (CWD) and Masked Generative Distillation (MGD), and output-level distillation via Kullback-Leibler divergence. Experiments on synthetic and real-world turbulence datasets demonstrate that JDATT achieves superior visual restoration and detection accuracy while significantly reducing model size and inference time, making it well-suited for real-time deployment.
Atmospheric Turbulence (AT) degrades the clarity and accuracy of surveillance imagery, posing challenges not only for visualization quality but also for object classification and scene tracking. Deep learning-based methods have been proposed to improve visual quality, but spatio-temporal distortions remain a significant issue. Although deep learning-based object detection performs well under normal conditions, it struggles to operate effectively on sequences distorted by atmospheric turbulence. In this paper, we propose a novel framework that learns to compensate for distorted features while simultaneously improving visualization and object detection. This end-to-end training strategy leverages and exchanges knowledge of low-level distorted features in the AT mitigator with semantic features extracted in the object detector. Specifically, in the AT mitigator a 3D Mamba-based structure is used to handle the spatio-temporal displacements and blurring caused by turbulence. Optimization is achieved through back-propagation in both the AT mitigator and object detector. Our proposed DMAT outperforms state-of-the-art AT mitigation and object detection systems up to a 15% improvement on datasets corrupted by generated turbulence.