arXiv subjects

Fan Li

Publications and source records attributed to Fan Li.

At least 145 records · Page 8Linked to original sources

arXiv2025

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles

Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, we design LiteED, a highly efficient alternative to the original computationally intensive VAE in SD, reducing parameters by 97.5% while preserving high-quality encoding and decoding. Additionally, we propose online annealing pruning for the U-Net, which progressively shifts generative priors from heavy modules to lightweight counterparts, ensuring effective knowledge transfer and further optimizing efficiency. To mitigate the loss of prior knowledge during pruning, we incorporate a multi-layer feature distillation loss. Through an in-depth analysis of each design component, we provide valuable insights for future research. PocketSR, with a model size of 146M parameters, processes 4K images in just 0.8 seconds, achieving a remarkable speedup over previous methods. Notably, it delivers performance on par with state-of-the-art single-step and even multi-step RealSR models, making it a highly practical solution for edge-device applications.

cs.CV↗

arXiv2025

Evaluating Informative Cluster Size in Cluster Randomized Trials

In cluster randomized trials, the average treatment effect among individuals (i-ATE) can be different from the cluster average treatment effect (c-ATE) when informative cluster size is present, i.e., when treatment effects or participant outcomes depend on cluster size. In such scenarios, mixed-effects models and generalized estimating equations (GEEs) with exchangeable correlation structure are biased for both the i-ATE and c-ATE estimands, whereas GEEs with an independence correlation structure or analyses of cluster-level summaries are recommended in practice. However, when cluster size is non-informative, mixed-effects models and GEEs with exchangeable correlation structure can provide unbiased estimation and notable efficiency gains over other methods. Thus, hypothesis tests for informative cluster size would be useful to assess this key phenomenon under cluster randomization. In this work, we develop model-based, model-assisted, and randomization-based tests for informative cluster size in cluster randomized trials. We construct simulation studies to examine the operating characteristics of these tests, show they have appropriate Type I error control and meaningful power, and contrast them to existing model-based tests used in the observational study setting. The proposed tests are then applied to data from a recent cluster randomized trial, and practical recommendations for using these tests are discussed.

stat.ME↗

arXiv2025

DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning

Deep graph models have achieved great success in network representation learning. However, their focus on pairwise relationships restricts their ability to learn pervasive higher-order interactions in real-world systems, which can be naturally modeled as hypergraphs. To tackle this issue, Hypergraph Neural Networks (HNNs) have garnered substantial attention in recent years. Despite the proposal of numerous HNNs, the absence of consistent experimental protocols and multi-dimensional empirical analysis impedes deeper understanding and further development of HNN research. While several toolkits for deep hypergraph learning (DHGL) have been introduced to facilitate algorithm evaluation, they provide only limited quantitative evaluation results and insufficient coverage of advanced algorithms, datasets, and benchmark tasks. To fill the gap, we introduce DHG-Bench, the first comprehensive benchmark for HNNs. Specifically, DHG-Bench systematically investigates the characteristics of HNNs in terms of four dimensions: effectiveness, efficiency, robustness, and fairness. We comprehensively evaluate 17 state-of-the-art HNN algorithms on 22 diverse datasets spanning node-, edge-, and graph-level tasks, under unified experimental settings. Extensive experiments reveal both the strengths and limitations of existing algorithms, offering valuable insights and directions for future research. Furthermore, to facilitate reproducible research, we have developed an easy-to-use library for training and evaluating different HNN methods. The DHG-Bench library is available at: https://github.com/Coco-Hut/DHG-Bench.

cs.LG↗

arXiv2025

UI2V-Bench: An Understanding-based Image-to-video Generation Benchmark

Generative diffusion models are developing rapidly and attracting increasing attention due to their wide range of applications. Image-to-Video (I2V) generation has become a major focus in the field of video synthesis. However, existing evaluation benchmarks primarily focus on aspects such as video quality and temporal consistency, while largely overlooking the model's ability to understand the semantics of specific subjects in the input image or to ensure that the generated video aligns with physical laws and human commonsense. To address this gap, we propose UI2V-Bench, a novel benchmark for evaluating I2V models with a focus on semantic understanding and reasoning. It introduces four primary evaluation dimensions: spatial understanding, attribute binding, category understanding, and reasoning. To assess these dimensions, we design two evaluation methods based on Multimodal Large Language Models (MLLMs): an instance-level pipeline for fine-grained semantic understanding, and a feedback-based reasoning pipeline that enables step-by-step causal assessment for more accurate evaluation. UI2V-Bench includes approximately 500 carefully constructed text-image pairs and evaluates a range of both open source and closed-source I2V models across all defined dimensions. We further incorporate human evaluations, which show strong alignment with the proposed MLLM-based metrics. Overall, UI2V-Bench fills a critical gap in I2V evaluation by emphasizing semantic comprehension and reasoning ability, offering a robust framework and dataset to support future research and model development in the field.

cs.CV↗

arXiv2025

Semiparametric principal stratification analysis beyond monotonicity

Intercurrent events, common in clinical trials and observational studies, affect the existence or interpretation of final outcomes. Principal stratification addresses this challenge by defining local average treatment effect estimands within subpopulations, but often relies on restrictive assumptions such as monotonicity and counterfactual intermediate independence. To overcome these limitations, we propose a semiparametric framework for principal stratification analysis leveraging a margin-free, conditional odds ratio sensitivity parameter. Under principal ignorability, we derive nonparametric identification formulas and efficient estimation methods, including a conditionally doubly robust parametric estimator and a debiased machine learning estimator with data-adaptive nuisance learners. Our simulations show that incorrectly assuming monotonicity can frequently lead to biased inference, but incorrectly assuming non-monotonicity when monotonicity holds may maintain approximately valid inference. We demonstrate our methods in the context of a critical care trial, where monotonicity is unlikely to be valid.

stat.ME↗

arXiv2025

Model-robust standardization in cluster-randomized trials

In cluster-randomized trials, generalized linear mixed models and generalized estimating equations have conventionally been the default analytic methods for estimating the average treatment effect as routine practice. However, recent studies have demonstrated that their treatment effect coefficient estimators may correspond to ambiguous estimands when the models are misspecified or when there exists informative cluster sizes. In this article, we present a unified approach that standardizes output from a given regression model to ensure estimand-aligned inference for the treatment effect parameters in cluster-randomized trials. We introduce estimators for both the cluster-average and the individual-average treatment effects (marginal estimands) that are always consistent regardless of whether the specified working regression models align with the unknown data generating process. We further explore the use of a deletion-based jackknife variance estimator for inference. The development of our approach also motivates a natural test for informative cluster size. Extensive simulation experiments are designed to demonstrate the advantage of the proposed estimators under a variety of scenarios. The proposed model-robust standardization methods are implemented in the MRStdCRT R package.

stat.ME↗

arXiv2025

What's the Weight? Estimating Controlled Outcome Differences in Complex Surveys for Health Disparities Research

In this work, we are motivated by the problem of estimating racial disparities in health outcomes, specifically the average controlled difference (ACD) in telomere length between Black and White individuals, using data from the National Health and Nutrition Examination Survey (NHANES). To do so, we build a propensity for race to properly adjust for other social determinants while characterizing the controlled effect of race on telomere length. Propensity score methods are broadly employed with observational data as a tool to achieve covariate balance, but how to implement them in complex surveys is less studied - in particular, when the survey weights depend on the group variable under comparison (as the NHANES sampling scheme depends on self-reported race). We propose identification formulas to properly estimate the ACD in outcomes between Black and White individuals, with appropriate weighting for both covariate imbalance across the two racial groups and generalizability. Via extensive simulation, we show that our proposed methods outperform traditional analytic approaches in terms of bias, mean squared error, and coverage when estimating the ACD for our setting of interest. In our data, we find that evidence of racial differences in telomere length between Black and White individuals attenuates after accounting for confounding by socioeconomic factors and utilizing appropriate propensity score and survey weighting techniques. Software to implement these methods and code to reproduce our results can be found in the R package svycdiff, available through the Comprehensive R Archive Network (CRAN) at cran.r-project.org/web/packages/svycdiff/, or in a development version on GitHub at github.com/salernos/svycdiff.

stat.ME↗

arXiv2025

SCREME: A Scalable Framework for Resilient Memory Design

The continuing advancement of memory technology has not only fueled a surge in performance, but also substantially exacerbate reliability challenges. Traditional solutions have primarily focused on improving the efficiency of protection schemes, i.e., Error Correction Codes (ECC), under the assumption that allocating additional memory space for parity data is always expensive and therefore not a scalable solution. We break the stereotype by proposing an orthogonal approach that provides additional, cost-effective memory space for resilient memory design. In particular, we recognize that ECC chips (used for parity storage) do not necessarily require the same performance level as regular data chips. This offers two-fold benefits: First, the bandwidth originally provisioned for a regular-performance ECC chip can instead be used to accommodate multiple low-performance chips. Second, the cost of ECC chips can be effectively reduced, as lower performance often correlates with lower expense. In addition, we observe that server-class memory chips are often provisioned with ample, yet underutilized I/O resources. This further offers the opportunity to repurpose these resources to enable flexible on-DIMM interconnections. Based on the above two insights, we finally propose SCREME, a scalable memory framework leverages cost-effective, albeit slower, chips -- naturally produced during rapid technology evolution -- to meet the growing reliability demands driven by this evolution.

cs.AR↗

arXiv2025

TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP

3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions, which is crucial for embodied intelligence. Existing 3D visual grounding methods typically rely on separate encoders for different modalities (e.g., RGB images, text, and 3D point clouds), resulting in large and complex models that are inefficient to train. While some approaches use pre-trained 2D multi-modal models like CLIP for 3D tasks, they still struggle with aligning point cloud data to 2D encoders. As a result, these methods continue to depend on 3D encoders for feature extraction, further increasing model complexity and training inefficiency. In this paper, we propose a unified 2D pre-trained multi-modal network to process all three modalities (RGB images, text, and point clouds), significantly simplifying the architecture. By leveraging a 2D CLIP bi-modal model with adapter-based fine-tuning, this framework effectively adapts to the tri-modal setting, improving both adaptability and performance across modalities. Our Geometric-Aware 2D-3D Feature Recovery and Fusion (GARF) module is designed to fuse geometric multi-scale features from point clouds and images. We then integrate textual features for final modality fusion and introduce a multi-modal decoder to facilitate deep cross-modal understanding. Together, our method achieves unified feature extraction and fusion across the three modalities, enabling an end-to-end 3D visual grounding model. Compared to the baseline, our method reduces the number of trainable parameters by approximately 58\%, while achieving a 6.52\% improvement in the 3D detection task and a 6.25\% improvement in the 3D visual grounding task.

cs.CV↗

arXiv2025

Unravelling the unique kinetic interactions between N2O and unsaturated hydrocarbons

The interaction between unsaturated hydrocarbons and N2O has attracted considerable attention in recent years due to their important roles as potential propellants for advanced propulsion systems e.g. NOFBX, key combustion intermediates in EGR systems, and as major pollutants and precursors in atmospheric chemistry. Although experimental studies and kinetic models have been developed to investigate its fuel chemistry, discrepancies remain between modeled and measured ignition delay times at low temperatures. In this work, we characterize previously unreported direct interaction pathways between N2O and unsaturated hydrocarbons C2H4, C3H6, C2H2, and C3H4 through quantum chemistry calculations, comprehensive kinetic modeling, and experimental validation. These reactions proceed via O-atom addition from N2O to unsaturated hydrocarbons, forming five membered ring intermediates that decompose into N2 and hydrocarbon specific products. Distinct mechanistic differences are identified between alkenes and alkynes, arising from the disparity in N C bond lengths within the intermediates 1.480 A vs. 1.381 A, which governs their decomposition pathways. The corresponding rate coefficients are determined and implemented into multiple kinetic models, with autoignition simulations showing a pronounced promoting effect on model reactivity and improved agreement with experiments, especially at low temperatures. Flux analysis further reveals that the new pathways suppress conventional inhibiting channels while enabling aldehyde and ketone forming pathways that enhance overall reactivity. This work provides a more complete description of N2O hydrocarbon interactions, advancing predictive capability for combustion and atmospheric chemistry.

physics.chem-ph↗

arXiv2025

Doubly robust estimation and sensitivity analysis with outcomes truncated by death in multi-arm clinical trials

In clinical trials, the observation of participant outcomes may frequently be hindered by death, leading to ambiguity in defining a scientifically meaningful final outcome for those who die. Principal stratification methods are valuable tools for addressing the average causal effect among always-survivors, i.e., the average treatment effect among a subpopulation defined as those who would survive regardless of treatment assignment. Although robust methods for the truncation-by-death problem in two-arm clinical trials have been previously studied, its expansion to multi-arm clinical trials remains elusive. In this article, we study the identification of a class of survivor average causal effect estimands with multiple treatments under monotonicity and principal ignorability, and first propose simple weighting and regression approaches for point estimation. As a further improvement, we derive the efficient influence function to motivate doubly robust estimators for the survivor average causal effects in multi-arm clinical trials. We also propose sensitivity methods under violations of key causal assumptions. Extensive simulations are conducted to investigate the finite-sample performance of the proposed methods against the existing methods, and a real data example is used to illustrate how to operationalize the proposed estimators and the sensitivity methods in practice.

stat.ME↗

arXiv2025

Multiply robust estimation for causal survival analysis with treatment noncompliance

Comparative effectiveness research frequently addresses a time-to-event outcome and can require unique considerations in the presence of treatment noncompliance. Motivated by the challenges in addressing noncompliance in the ADAPTABLE pragmatic clinical trial, we develop a multiply robust estimator to estimate the principal survival causal effects under the principal ignorability and monotonicity. The multiply robust estimator is consistent even if one, and sometimes two, of the required models are misspecified. We apply the multiply robust method in the ADAPTABLE trial to evaluate the effect of low- versus high-dose aspirin assignment on patients' death and hospitalization from cardiovascular diseases. We find that, comparing to low-dose assignment, assignment to the high-dose leads to differential effects among always high-dose takers, compliers, and always low-dose takers. Such treatment effect heterogeneity contributes to the null intention-to-treatment effect. We further perform a formal sensitivity analysis for investigating the robustness of our causal conclusions under violation of two identification assumptions specific to noncompliance.

stat.ME↗

arXiv2025

RecGPT Technical Report

Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem.

cs.IR↗

arXiv2025

Envelope Control Enabled Probabilistic Shaping for Peak Power Constrained IM DD Systems

Probabilistic shaping (PS) has attracted significant attention in intensity-modulation and direct-detection (IM-DD) systems. However, due to the unique system model and inherent constraints, the effective application of the PS technique is still an open question in IM-DD systems, particularly in systems with memory effects. In this paper, a novel indirect PS scheme tailored for peak power constrained (PPC) IM-DD systems is proposed. The key idea lies in strategically controlling the signal envelope to mitigate memory-induced impairments, such as nonlinearity, overshoot, peak-to-average power ratio enhancement, etc. The proposed scheme incorporates a dynamic selective mapping (DSLM) mechanism at the transmitter, enabling an untypical bit-to-symbol mapping in which the current symbol is not only determined by the current bits pattern but also by previously generated symbols within a specified memory length. At the receiver side, a turbo equalizer with a modified M-BCJR algorithm is proposed to achieve the recovery of ambiguous bits induced by DSLM. Experimental verification in a 56GBaud PAM8 system demonstrates that the proposed scheme exhibits 1dB receiver sensitivity improvement over 2km single-mode fiber transmission. In addition, the proposed scheme has also been demonstrated to be compatible with the typical probabilistic amplitude shaping architecture, enabling a simple and fine-granularity rate adaptation capability. To the best of our knowledge, this work opens a new sight for the application of the PS technique in PPC IM-DD systems with memory effects.

eess.SP↗

arXiv2025

HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs

Video Anomaly Detection (VAD) aims to identify and locate deviations from normal patterns in video sequences. Traditional methods often struggle with substantial computational demands and a reliance on extensive labeled datasets, thereby restricting their practical applicability. To address these constraints, we propose HiProbe-VAD, a novel framework that leverages pre-trained Multimodal Large Language Models (MLLMs) for VAD without requiring fine-tuning. In this paper, we discover that the intermediate hidden states of MLLMs contain information-rich representations, exhibiting higher sensitivity and linear separability for anomalies compared to the output layer. To capitalize on this, we propose a Dynamic Layer Saliency Probing (DLSP) mechanism that intelligently identifies and extracts the most informative hidden states from the optimal intermediate layer during the MLLMs reasoning. Then a lightweight anomaly scorer and temporal localization module efficiently detects anomalies using these extracted hidden states and finally generate explanations. Experiments on the UCF-Crime and XD-Violence datasets demonstrate that HiProbe-VAD outperforms existing training-free and most traditional approaches. Furthermore, our framework exhibits remarkable cross-model generalization capabilities in different MLLMs without any tuning, unlocking the potential of pre-trained MLLMs for video anomaly detection and paving the way for more practical and scalable solutions.

cs.CV↗

arXiv2025

Composed Multi-modal Retrieval: A Survey of Approaches and Applications

The burgeoning volume of multi-modal data necessitates advanced retrieval paradigms beyond unimodal and cross-modal approaches. Composed Multi-modal Retrieval (CMR) emerges as a pivotal next-generation technology, enabling users to query images or videos by integrating a reference visual input with textual modifications, thereby achieving unprecedented flexibility and precision. This paper provides a comprehensive survey of CMR, covering its fundamental challenges, technical advancements, and applications. CMR is categorized into supervised, zero-shot, and semi-supervised learning paradigms. We discuss key research directions, including data construction, model architecture, and loss optimization in supervised CMR, as well as transformation frameworks and linear integration in zero-shot CMR, and semi-supervised CMR that leverages generated pseudo-triplets while addressing data noise/uncertainty. Additionally, we extensively survey the diverse application landscape of CMR, highlighting its transformative potential in e-commerce, social media, search engines, public security, etc. Seven high impact application scenarios are explored in detail with benchmark data sets and performance analysis. Finally, we further provide new potential research directions with the hope of inspiring exploration in other yet-to-be-explored fields. A curated list of works is available at: https://github.com/kkzhang95/Awesome-Composed-Multi-modal-Retrieval

cs.IR↗

arXiv2025

RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction

Blind facial image restoration is highly challenging due to unknown complex degradations and the sensitivity of humans to faces. Although existing methods introduce auxiliary information from generative priors or high-quality reference images, they still struggle with identity preservation problems, mainly due to improper feature introduction on detailed textures. In this paper, we focus on effectively incorporating appropriate features from high-quality reference images, presenting a novel blind facial image restoration method that considers reference selection, transfer, and reconstruction (RefSTAR). In terms of selection, we construct a reference selection (RefSel) module. For training the RefSel module, we construct a RefSel-HQ dataset through a mask generation pipeline, which contains annotating masks for 10,000 ground truth-reference pairs. As for the transfer, due to the trivial solution in vanilla cross-attention operations, a feature fusion paradigm is designed to force the features from the reference to be integrated. Finally, we propose a reference image reconstruction mechanism that further ensures the presence of reference image features in the output image. The cycle consistency loss is also redesigned in conjunction with the mask. Extensive experiments on various backbone models demonstrate superior performance, showing better identity preservation ability and reference feature transfer quality. Source code, dataset, and pre-trained models are available at https://github.com/yinzhicun/RefSTAR.

cs.CV↗

arXiv2025

OutDreamer: Video Outpainting with a Diffusion Transformer

Video outpainting is a challenging task that generates new video content by extending beyond the boundaries of an original input video, requiring both temporal and spatial consistency. Many state-of-the-art methods utilize latent diffusion models with U-Net backbones but still struggle to achieve high quality and adaptability in generated content. Diffusion transformers (DiTs) have emerged as a promising alternative because of their superior performance. We introduce OutDreamer, a DiT-based video outpainting framework comprising two main components: an efficient video control branch and a conditional outpainting branch. The efficient video control branch effectively extracts masked video information, while the conditional outpainting branch generates missing content based on these extracted conditions. Additionally, we propose a mask-driven self-attention layer that dynamically integrates the given mask information, further enhancing the model's adaptability to outpainting tasks. Furthermore, we introduce a latent alignment loss to maintain overall consistency both within and between frames. For long video outpainting, we employ a cross-video-clip refiner to iteratively generate missing content, ensuring temporal consistency across video clips. Extensive evaluations demonstrate that our zero-shot OutDreamer outperforms state-of-the-art zero-shot methods on widely recognized benchmarks.

cs.CV↗