arXiv subjects

Qian Zeng

Publications and source records attributed to Qian Zeng.

11 recordsLinked to original sources

arXiv2026

Democratizing and accelerating AI-driven pathology research through agentic intelligence

Computational pathology has advanced rapidly with the emergence of foundation models, yet widespread adoption remains limited by substantial technical complexity and programming requirements. Here we present PathLab, an autonomous agentic framework that translates natural-language research objectives into executable and validated computational pathology workflows through the structured composition of domain-specific skills and tools. By organizing workflow generation around reusable methodological modules, including data preprocessing, model development, evaluation and interpretation, PathLab enables studies to be specified at the level of scientific intent rather than implementation details. We evaluated PathLab across 12 public datasets spanning four representative task families: region-of-interest classification, whole-slide image classification, segmentation and survival prediction. Across all task categories, PathLab achieved non-inferior performance relative to expert implementations, while consistently enforcing semantic validity of user prompts and proactively rejecting incompatible workflow specifications prior to execution. In controlled user studies, PathLab substantially reduced the time required to generate executable analytical pipelines and enabled domain experts without programming experience to independently design, execute and evaluate computational pathology studies. Together, these results establish PathLab as a reliable interface between biomedical intent and computational execution, enabling computational pathology studies to be designed at the level of scientific questions rather than programming expertise. By lowering technical barriers to advanced AI methodologies, PathLab provides a foundation for the broader democratization of computational pathology.

cs.AI↗

arXiv2025

MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image

Whole-slide images (WSIs) are an important data modality in computational pathology, yet their gigapixel resolution and lack of fine-grained annotations challenge conventional deep learning models. Multiple instance learning (MIL) offers a solution by treating each WSI as a bag of patch-level instances, but effectively modeling ultra-long sequences with rich spatial context remains difficult. Recently, Mamba has emerged as a promising alternative for long sequence learning, scaling linearly to thousands of tokens. However, despite its efficiency, it still suffers from limited spatial context modeling and memory decay, constraining its effectiveness to WSI analysis. To address these limitations, we propose MambaMIL+, a new MIL framework that explicitly integrates spatial context while maintaining long-range dependency modeling without memory forgetting. Specifically, MambaMIL+ introduces 1) overlapping scanning, which restructures the patch sequence to embed spatial continuity and instance correlations; 2) a selective stripe position encoder (S2PE) that encodes positional information while mitigating the biases of fixed scanning orders; and 3) a contextual token selection (CTS) mechanism, which leverages supervisory knowledge to dynamically enlarge the contextual memory for stable long-range modeling. Extensive experiments on 20 benchmarks across diagnostic classification, molecular prediction, and survival analysis demonstrate that MambaMIL+ consistently achieves state-of-the-art performance under three feature extractors (ResNet-50, PLIP, and CONCH), highlighting its effectiveness and robustness for large-scale computational pathology

cs.CV↗

arXiv2025

Information-Assisted Carnot Engine Surpasses Standard Thermodynamic Bounds

Information can improve heat engine performance, but the underlying principles are still not so clear. Here we introduce a Carnot information machine (CIE) and obtain a quantitative relationship between the engine performance and information. We demonstrate that the presence of information changes allows the CIE to operate as a heat engine in the regime where the standard Carnot cycle is prohibited, ensures that the efficiency of the CIE is greater than or equal to the standard Carnot efficiency, and significantly enables it to achieve 100\% efficiency with positive work extraction for arbitrary two-level systems. We explicitly demonstrate these features using a spin-1/2 system and propose an experimental implementation scheme based on a trapped $^{40}\mathrm{Ca}^+$ ion.

cond-mat.stat-mech↗

arXiv2025

Diffusion Model Quantization: A Review

Recent success of large text-to-image models has empirically underscored the exceptional performance of diffusion models in generative tasks. To facilitate their efficient deployment on resource-constrained edge devices, model quantization has emerged as a pivotal technique for both compression and acceleration. This survey offers a thorough review of the latest advancements in diffusion model quantization, encapsulating and analyzing the current state of the art in this rapidly advancing domain. First, we provide an overview of the key challenges encountered in the quantization of diffusion models, including those based on U-Net architectures and Diffusion Transformers (DiT). We then present a comprehensive taxonomy of prevalent quantization techniques, engaging in an in-depth discussion of their underlying principles. Subsequently, we perform a meticulous analysis of representative diffusion model quantization schemes from both qualitative and quantitative perspectives. From a quantitative standpoint, we rigorously benchmark a variety of methods using widely recognized datasets, delivering an extensive evaluation of the most recent and impactful research in the field. From a qualitative standpoint, we categorize and synthesize the effects of quantization errors, elucidating these impacts through both visual analysis and trajectory examination. In conclusion, we outline prospective avenues for future research, proposing novel directions for the quantization of generative models in practical applications. The list of related papers, corresponding codes, pre-trained models and comparison results are publicly available at the survey project homepage https://github.com/TaylorJocelyn/Diffusion-Model-Quantization.

cs.CV↗

arXiv2025

Sampling-Aware Quantization for Diffusion Models

Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and resource-limited environments. Previous research has endeavored to address these limitations in a decoupled manner, utilizing either advanced samplers or efficient model quantization techniques. In this study, we uncover that quantization-induced noise disrupts directional estimation at each sampling step, further distorting the precise directional estimations of higher-order samplers when solving the sampling equations through discretized numerical methods, thereby altering the optimal sampling trajectory. To attain dual acceleration with high fidelity, we propose a sampling-aware quantization strategy, wherein a Mixed-Order Trajectory Alignment technique is devised to impose a more stringent constraint on the error bounds at each sampling step, facilitating a more linear probability flow. Extensive experiments on sparse-step fast sampling across multiple datasets demonstrate that our approach preserves the rapid convergence characteristics of high-speed samplers while maintaining superior generation quality. Code is publicly available at: https://github.com/TaylorJocelyn/Sampling-aware-Quantization.

cs.CV↗

arXiv2025

Using Subgraph GNNs for Node Classification:an Overlooked Potential Approach

Previous studies have demonstrated the strong performance of Graph Neural Networks (GNNs) in node classification. However, most existing GNNs adopt a node-centric perspective and rely on global message passing, leading to high computational and memory costs that hinder scalability. To mitigate these challenges, subgraph-based methods have been introduced, leveraging local subgraphs as approximations of full computational trees. While this approach improves efficiency, it often suffers from performance degradation due to the loss of global contextual information, limiting its effectiveness compared to global GNNs. To address this trade-off between scalability and classification accuracy, we reformulate the node classification task as a subgraph classification problem and propose SubGND (Subgraph GNN for NoDe). This framework introduces a differentiated zero-padding strategy and an Ego-Alter subgraph representation method to resolve label conflicts while incorporating an Adaptive Feature Scaling Mechanism to dynamically adjust feature contributions based on dataset-specific dependencies. Experimental results on six benchmark datasets demonstrate that SubGND achieves performance comparable to or surpassing global message-passing GNNs, particularly in heterophilic settings, highlighting its effectiveness and scalability as a promising solution for node classification.

cs.LG↗

arXiv2025

D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models

Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained scenarios. Post-training quantization (PTQ) compresses and accelerates diffusion models without retraining, but it inevitably introduces additional quantization noise, resulting in mean and variance deviations. In this work, we propose D2-DPM, a dual denoising mechanism aimed at precisely mitigating the adverse effects of quantization noise on the noise estimation network. Specifically, we first unravel the impact of quantization noise on the sampling equation into two components: the mean deviation and the variance deviation. The mean deviation alters the drift coefficient of the sampling equation, influencing the trajectory trend, while the variance deviation magnifies the diffusion coefficient, impacting the convergence of the sampling trajectory. The proposed D2-DPM is thus devised to denoise the quantization noise at each time step, and then denoise the noisy sample through the inverse diffusion iterations. Experimental results demonstrate that D2-DPM achieves superior generation quality, yielding a 1.42 lower FID than the full-precision model while achieving 3.99x compression and 11.67x bit-operation acceleration.

cs.CV↗

arXiv2024

FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training

Fundus images are essential for the early screening and detection of eye diseases. While deep learning models using fundus images have significantly advanced the diagnosis of multiple eye diseases, variations in images from different imaging devices and locations (known as domain shifts) pose challenges for deploying pre-trained models in real-world applications. To address this, we propose a novel Fundus On-the-fly Test-Time Adaptation (FunOTTA) framework that effectively generalizes a fundus image diagnosis model to unseen environments, even under strong domain shifts. FunOTTA stands out for its stable adaptation process by performing dynamic disambiguation in the memory bank while minimizing harmful prior knowledge bias. We also introduce a new training objective during adaptation that enables the classifier to incrementally adapt to target patterns with reliable class conditional estimation and consistency regularization. We compare our method with several state-of-the-art test-time adaptation (TTA) pipelines. Experiments on cross-domain fundus image benchmarks across two diseases demonstrate the superiority of the overall framework and individual components under different backbone networks. Code is available at https://github.com/Casperqian/FunOTTA.

cs.CV↗

arXiv2022

Conditional entropy production and quantum fluctuation theorem of dissipative information: Theory and experiments

We study quantum conditional entropy production, which quantifies the irreversibility of system-environment evolution from the perspective of a third system, called the reference. The reference is initially correlated with the system. We show that the quantum unconditional entropy production with respect to the system is less than the conditional entropy production with respect to the reference, where the latter includes a reference-induced dissipative information. The dissipative information pinpoints the distributive correlation established between the environment and the reference, even though they do not interact directly. When reaching the thermal equilibrium, the system-environment evolution has a zero unconditional entropy production. However, one can still have a nonzero conditional entropy production with respect to the reference, which characterizes the informational nonequilibrium of the system-environment evolution in the view point of the reference. The additional contribution to the conditional entropy production, the dissipative information, characterizes a minimal thermodynamic cost that the system pays for maintaining the correlation with the reference. Positive dissipative information also characterizes potential work waste. We prove that both types of entropy production and the dissipative information follow quantum fluctuation theorems when a two-point measurement is applied. We verify the quantum fluctuation theorem for the dissipative information experimentally on IBM quantum computers. We also present examples based on the qubit collisional model and demonstrate universal nonzero dissipative information in the qubit Maxwell's demon protocol.

quant-ph↗

arXiv2020

New Fluctuation Theorem on Maxwell's Demon

With the increasing interest for the control of the system at the nano and mesoscopic scales, studies have been focused on the limit of the energy dissipation in an open system by refining the concept of the Maxwell's demon. The well-known Sagawa-Ueda fluctuation theorem provides an explanation of the demon: the absence of a part of demon's information leads to an improper entropy production which violates the thermodynamic 2nd law. Realizing that the demon contributes not only to the system but also to the environments, we introduce the dissipative information to quantify the total contribution of the demon, rather than using an improper entropy production. We prove a set of new fluctuation theorems based on this, which can be used to uncover the truth behind the demon: The controlled system does not violate the 2nd law at any coarse-grained level for the demon's control. However, there exists an inevitable demon-induced dissipative information which always increases the entropy production. A consequence of these theorems is that, less work and more heat can be extracted and generated respectively by a demon than the limits predicted by the Ueda-Sagawa theorem. We also suggest a possible realization of the experimental estimation of these work and heat bounds, which can be measured and tested.

cond-mat.stat-mech↗

arXiv2017

Information Landscape and Flux, Mutual Information Rate Decomposition and Entropy Production

We explore the dynamics of information systems. We show that the driving force for information dynamics is determined by both the information landscape and information flux which determines the equilibrium time reversible and the nonequilibrium time-irreversible behaviours of the system respectively. We further demonstrate that the mutual information rate between the two subsystems can be decomposed into the time-reversible and time-irreversible parts respectively, analogous to the information landscape-flux decomposition for dynamics. Finally, we uncover the intimate relation between the nonequilibrium thermodynamics in terms of the entropy production rates and the time-irreversible part of the mutual information rate. We demonstrate the above features by the dynamics of a bivariate Markov chain.

cond-mat.stat-mech↗