arXiv subjects

Fan Li

Publications and source records attributed to Fan Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Randomization inference for stepped-wedge designs with noncompliance with application to a palliative care pragmatic trial

While palliative care is increasingly commonly delivered to hospitalized patients with serious illnesses, few studies have estimated its causal effects. Courtright et al. (2016) adopted a stepped-wedge cluster-randomized design to assess the effect of palliative care on a patient-centered outcome. The randomized intervention was a nudge to administer palliative care but did not guarantee receipt of palliative care, resulting in noncompliance. A subsequent analysis using methods suited for standard trial designs produced statistically anomalous results, as an intention-to-treat analysis found no effect while an instrumental variable analysis did (Courtright et al. 2024). This highlights the need for a more principled approach to address noncompliance in stepped-wedge designs. We provide a formal causal inference framework for the stepped-wedge design with noncompliance by introducing a relevant causal estimand and corresponding estimators and inferential procedures. Through numerical studies, we compare an array of estimators and provide practical guidance in choosing an analysis method. Finally, we apply our recommended methods to reanalyze the palliative care pragmatic trial, producing point estimates suggesting a larger effect than the original analysis, but intervals that did not reach statistical significance.

stat.ME↗

arXiv2026

A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models

Vision-language-action (VLA) models predict sequential actions to execute tasks specified by language instructions, conditioned on visual observations and proprioceptive states. However, how to fuse modalities in VLA models remains an open problem, since robot manipulation involves dynamic phases, such as long-distance movements and close-range interactions, in which the importance of visual observations may vary over time. In this paper, we propose an infer-diagnose-refine (IDR) framework, a model-agnostic framework that can be integrated with diverse VLA architectures for refining action predictions at test time. IDR first infers actions under factual and counterfactual scenarios of visual observations, and then diagnoses the causal effects of visual observations as the estimated dynamic importance, which is finally used to refine the action predictions in a training-free manner. We further design a causality-aware action refiner to realize the IDR framework, including zero-padding interventions for inferring counterfactual actions, norm-based quantification for diagnosing causal effects, and gated residual fusion for refining actions. Extensive experiments on both simulation benchmarks and real-world tasks show improvements in overall performance across multiple VLA backbones, demonstrating the efficacy of dynamically adjusting visual importance at test time.

cs.RO↗

arXiv2026

Bayesian change-plane regression

Change-plane regression represents treatment effect heterogeneity through an interpretable rule that assigns patients to two groups according to whether a linear score of baseline covariates crosses a threshold. Although easy to communicate, likelihood-based inference for the hard threshold is nonregular, invalidating standard large-sample approximations. We develop a Bayesian framework that replaces the sharp indicator with a smooth probit gate at a declared smoothing scale and treats the smoothed subgroup rule as the reported estimand. At a fixed smoothing scale, the posterior satisfies a misspecified Bernstein--von Mises theorem centered at the smoothed rule. Under a vanishing smoothing schedule, the posterior learns the boundary faster than the parametric rate, while within an explicit schedule window the regression block and treatment-effect contrast satisfy a Bernstein--von Mises theorem centered at the hard-threshold values with known-subgroup oracle efficiency. Thus, effect inference pays no first-order price for regularization. A decision-theoretic reporting protocol with consistency guarantees separates evidence of heterogeneity from reporting a boundary. Computation uses latent-variable augmentation, a great-circle elliptical slice sampler, and a normalized horseshoe prior. Simulations and an application to the PREMIER trial illustrate the method.

stat.ME↗

arXiv2026

DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition

Split face recognition reduces client-side computation but exposes intermediate features to feature inversion attacks and unauthorized analysis by honest-but-curious (HBC) servers. Existing privacy-preserving face recognition methods mainly aim to resist unauthorized reconstruction, typically producing features whose inversion yields visibly degraded results, which may reveal the existence of protection and motivate adaptive attacks. To address this issue, we propose DecoyFace, an imperceptible decoy-oriented framework that steers unauthorized reconstruction toward a plausible but incorrect identity while preserving recognition utility. The key idea is to decompose the intermediate representation into a reconstruction-sensitive subspace and its complementary subspace. The client injects decoy identity cues into the reconstruction-sensitive subspace, while limited recognition-relevant evidence from the true sample is retained in the complementary subspace. On the server side, an authorized canonicalization module suppresses decoy-dominant components and recovers a recognition-friendly representation. This design addresses both attacker-side inversion from intercepted features and HBC server-side reconstruction from canonicalized representations. Experiments show that DecoyFace preserves competitive recognition accuracy while substantially reducing identity leakage to 2.93% under U-Net attacks and 0.74% under Flow-Matching attacks while yielding visually plausible and imperceptible reconstructions, with over 99.78% face validity on LFW dataset.

cs.CV↗

arXiv2026

The Resolution of Causal Heterogeneity

Causal subgroup analyses often report a small number of groups summarizing treatment effect heterogeneity, as if that number were a well-defined estimand. Outside genuinely latent class populations, however, a ``true'' subgroup count is model dependent rather than a population functional. We replace it with a new population estimand, the resolution profile, a functional of the causal feature law giving the fewest groups explaining a prescribed fraction of causal heterogeneity, defined for every population without latent structure. Inference is organized around one cross-fitted Bayesian-bootstrap posterior for a single structured moment process, its scores corrected with influence functions, so that paths, profiles, fixed-resolution summaries, and subgroup effects follow by composition. A uniform conditional Bernstein--von Mises theorem over a loss class containing the nonsmooth quantization losses shows this posterior merges with the efficient Gaussian limit under stated nuisance-rate and margin conditions. Subgroup-number uncertainty is not model selection but threshold nonregularity, the profile being an integer-valued threshold of a continuous path, discontinuous in the law at each knot. At these knots no single-valued selector is locally uniformly consistent over root-$n$ neighborhoods, and the set-valued report obtained by inverting a simultaneous band retains locally uniform validity over exactly the same perturbations. Simulations support the approximations, and an analysis of the MineThatData e-mail experiment illustrates the resolution-indexed report, in which two to three groups summarize the visit response while finer structure falls below a noise-floor diagnostic.

stat.ME↗

arXiv2026

Learning-Driven Adaptive Audit Scheduling: A Sequential Decision Approach to Off-Chain Data Integrity

We model cryptographic auditing of off-chain data as a Constrained MDP (CMDP) under partial observability: the storage node's hidden type and corruption state make the problem a POMDP, while a miss-rate ceiling rho imposes an explicit security constraint. We propose DRQN-CMDP, a Deep Recurrent Q-Network whose GRU layer maintains a belief over the latent node type, paired with Lagrangian dual ascent that adapts the miss-rate penalty lambda automatically. A pairing-free homomorphic-MAC primitive supplies O(1) on-chain verification cost. Across 13 methods--four DQN variants, PPO, A2C, PPO-Lagrangian, a stateful Bayesian heuristic, three fixed-rule baselines, and an oracle-informed heuristic--DRQN-CMDP achieves a favourable balance: 83% lower gas than fixed high-frequency auditing, single-digit miss rate (7.5%), and moderate detection latency--a combination no other method matches across all three objectives simultaneously.

cs.AI↗

arXiv2026

KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices

Functional fitness movements are widely used in training, competition, and health-oriented exercise programs, yet consistently enforcing repetition (rep) standards remains challenging due to subjective human judgment, time constraints, and evolving rules. Existing AI-based approaches mainly rely on learned scoring or reference-based comparisons and lack explicit rule-based approaches, limiting transparency and deterministic rep-level validation. To address these limitations, we propose KD-Judge, a novel knowledge-driven automated judging framework for functional fitness movements. It converts unstructured rulebook standards into executable, machine-readable representations using an LLM-based retrieval-augmented generation and chain-of-thought rule-structuring pipeline. The structured rules are then incorporated by a deterministic rule-based judging system with pose-guided kinematic reasoning to assess rep validity and temporal boundaries. To improve efficiency on edge devices, including a high-performance desktop and the resource-constrained Jetson AGX Xavier, we introduce a dual strategy caching mechanism that can be selectively applied to reduce redundant and unnecessary computation. Experiments demonstrate reliable rule-structuring performance and accurate rep-level assessment, with judgment evaluation conducted on the CFRep dataset, achieving faster-than-real-time execution (real-time factor (RTF) < 1). When the proposed caching strategy is enabled, the system achieves up to 3.36x and 15.91x speedups on resource-constrained edge device compared to the non-caching baseline for pre-recorded and live-streaming scenarios, respectively. These results show that KD-Judge enables transparent, efficient, and scalable rule-grounded rep-level analysis that can complement human judging in practice.

cs.CV↗

arXiv2026

Reliable Associative Lookup in Content-Addressable Memory

Content Addressable Memory (CAM) is an important memory paradigm, which performs fast search by comparing an input query against all stored entries in parallel, achieving $O(1)$ lookup complexity. CAM is typically built upon conventional memory technologies, such as SRAM and Non-Volatile Memory (NVM). Accordingly, CAM can also be subject to the reliability challenges of these underlying technologies. In traditional memory systems, protection codes play a critical role in ensuring reliability and have been extensively studied. However, protection codes for CAM have remained largely unexplored. This paper takes an initial step toward addressing this longstanding gap by introducing a non-traditional code design.

cs.AR↗

arXiv2026

Remote magnon-phonon entanglement in the waveguide-magnomechanics

Generating long-distance quantum entanglement is crucial for advancing quantum information processing. In this work, we propose a protocol for generating remote magnon-phonon entanglement in a hybrid waveguide-magnomechanical system, where multiple spatially separated magnon modes couple to a common waveguide while interacting with their respective phonon modes. By applying tailored pulsed drives and engineering the magnomechanical interactions, our scheme enables the creation of diverse long-distance and dynamically stable entanglement. Beyond basic magnon-phonon two-mode entanglement, it supports genuine multimode entanglement between a single phonon and multiple magnons, bipartite entanglement between a single magnon and multiple phonons, as well as genuine four-mode entanglement involving two magnons and two phonons. Moreover, we show that dissipative magnon-magnon interactions mediated by traveling photons can generate substantially stronger remote entanglement than coherent couplings. Our work provides an experimentally feasible scheme for the remote generation of magnon-phonon entanglement.

quant-ph↗

arXiv2026

Model-robust standardization in stepped wedge cluster randomized trials

Stepped-wedge cluster-randomized trials (SW-CRTs) are widely used in healthcare and implementation science, enabling all clusters to receive the intervention through a staggered rollout. Traditional model-based methods, including generalized estimating equations and mixed models, yield estimates that depend on implicit weighting schemes and parametric assumptions, and therefore may target ambiguous estimands under model misspecification. In this article, we propose a model-robust standardization framework for SW-CRTs that generalizes existing methods from parallel-arm CRTs to address informative sizes. We define causal estimands including horizontal-individual, horizontal-cluster, vertical-individual, and vertical-cluster average treatment effects under a super population framework and introduce a simple procedure that standardizes parametric and semiparametric working models for estimand-aligned analysis. For any specified working model, the resulting estimators remain consistent for their target estimands even if the working regression model is misspecified; moreover, their efficiency improves as the working model more closely approximates the true data-generating process. We evaluate the finite-sample properties of our proposed estimators through extensive simulations. Finally, we illustrate the application of our methods through reanalyses of two real-world SW-CRTs.

stat.ME↗

arXiv2026

Doubly cross-fit debiased machine learning of heterogeneous treatment effects under principal stratification

Principal stratification provides a foundational framework for causal inference with intermediate outcomes by defining causal effects within subpopulations, yet existing work has largely focused on average effects across strata rather than treatment effect heterogeneity within strata. Such within-stratum heterogeneity informs individualized treatment decisions but the associated methods are sparse. We address this gap by studying the identification and estimation of the conditional principal causal effects under principal ignorability combined with an odds ratio sensitivity parameterization, which relaxes the monotonicity assumption. To efficiently learn these estimands, we propose a novel doubly cross-fit doubly robust machine learner that resolves the nested nuisance structure inherent to principal stratification. Leveraging sequential orthogonal debiased machine learning with regularized least-squares sieves, we derive $\mathcal{L}^2$ and uniform limit theory, establish oracle efficiency, and construct uniform confidence bands for the proposed estimator. We use simulations to demonstrate the finite-sample performance of our estimator, and provide an empirical analysis of a randomized trial in acute lung injury, revealing informative patterns of treatment effect heterogeneity within the always-survivor subpopulation.

stat.ME↗

arXiv2026

Making censored pairs count: conditional tie weighting for win statistics with composite survival endpoints

Hierarchical composite endpoints are increasingly used in clinical trials to compare patients first on the most clinically important outcome and then, only when that comparison is tied, on lower priority outcomes. Under right censoring, a lower priority comparison may already be observed but still cannot contribute because the higher priority genuine tie required for descent through the hierarchy is not confirmed. Existing restricted win-statistic estimators address censoring by requiring such ties from higher priority to be observed as genuine ties. This all-or-nothing rule preserves the restricted-time estimand, but excludes pairs with censoring-induced ties even when their lower priority comparisons contain useful information. We propose conditional tie weighting, which replaces the unavailable higher priority genuine-tie indicator by its conditional probability given the observed pairwise data. The resulting estimator targets the same restricted-time win probabilities while allowing partially observed pairs to contribute fractionally when their lower priority comparison is informative. We establish identification and large-sample theory for the resulting two-sample U-statistics with estimated nuisance functions, and derive sandwich variance estimators for the win ratio, net benefit, and win odds. Simulations show substantial efficiency gains, especially under heavier censoring and longer restriction horizons. A reanalysis of the HF-ACTION trial illustrates how conditional tie weighting recovers information from censoring-induced ties in death-first hospitalization comparisons further apply our estimator to reanalyze a completed randomized clinical trial.

stat.ME↗

arXiv2026

InstanceControl: Controllable Complex Image Generation without Instance Labeling

Controllable image generation methods, such as ControlNet, have demonstrated a remarkable capacity to introduce visual conditions(e.g., depth maps) to guide image generation. However, these methods often struggle with complex multi-instance scenes, frequently leading to attribute confusion among instances. While recent approaches attempt to mitigate this via manual instance labeling, such requirements are labor-intensive. In this paper, we propose InstanceControl, a novel multi-instance controllable generation method that eliminates the need for instance labeling. We identify the primary bottleneck in existing methods as the inability to accurately associate instance descriptions with their corresponding regions within visual conditions. To address this, we leverage the Vision-Language Model (VLM) to establish instance-level correspondences between text prompts and visual conditions. Specifically, the VLM automatically parses instance descriptions from the text prompts and simultaneously predicts instance masks based on the visual conditions. Furthermore, since the predicted masks may contain noise, we introduce an adaptive mask refinement strategy that dynamically refines these instance masks during the generation process. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods, achieving superior fidelity and precise instance-level control.

cs.CV↗

arXiv2026

SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates

Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (bpp < 0.05), limiting its reliable deployment in bandwidth-constrained scenarios such as 6G semantic communications. This inconsistency stems from incomplete guidance information, which introduces semantic ambiguity into the generation process and may lead to natural-looking but source-inconsistent content. In this work, we propose a Semantic-Disambiguation-Guided Generative Image Compression (SDGIC) framework to constrain diffusion-based reconstruction at ultra-low bitrates. Specifically, SDGIC compresses the source image into three compact and complementary guidance streams: a concise text caption for global semantics, a highly compressed image (HCI) for dense visual evidence, and Reconstruction-Aware Semantic Residual Tokens (RSRTs) for reconstruction-relevant residual semantics that remain ambiguous under the text caption and HCI conditions. The RSRTs are directly optimized toward the downstream denoising objective, enabling them to provide source-specific semantic constraints for disambiguating diffusion-based reconstruction. To inject these three guidance streams into the generation process effectively, we design a Dual-Path Conditioned Diffusion Decoder (DPCD), which uses cross-attention for semantic conditions and ControlNet residuals for dense visual guidance. Extensive experiments demonstrate that SDGIC improves semantic consistency at ultra-low bitrates while maintaining favorable perceptual quality, with a 23.4% reduction in AFINE on the CLIC2020 dataset.

cs.CV↗

arXiv2026

Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

The advancement of generative AI models capable of producing text and image marks a critical step forward in the realm of multimodal intelligence, particularly for tasks involving the interleaving of both modalities. To advance this intelligence to the next stage, it is crucial for models to autonomously generate free-form interleaved text-image sequences. In this paper, we introduce ILLUME-X, an advanced unified multimodal paradigm that enables high-quality, free-form interleaved text-image generation by improving multimodal data efficiency and stabilizing the multimodal training process. ILLUME-X comprises three key components: (i) an expanded training data pipeline optimized for interleaved text-image generation, (ii) a progressive training strategy with self-adaptive objectives for free-length multimodal token sequences, and (iii) an objective and comprehensive evaluation method ILScore for interleaved text-image sequences. Notably, our ILLUME-X outperforms previous unified models across multiple interleaved text-image generation tasks like style transfer, image decomposition and storytelling.

cs.CV↗

arXiv2026

From Bootstrapping to Sequence Modeling: A Unified Generative Framework for Personalized Landing-Page Modeling

Modern online platforms increasingly adopt multi-page architectures to accommodate diverse user needs. On these platforms, page navigation (the process of directing users to specific functional pages upon app entry) serves as a critical gateway that shapes user's first impression and significantly influences subsequent engagement. To optimize this process, Kuaishou formulated the task of Personalized Landing Page Modeling (PLPM) and proposed KLAN, a reinforcement learning framework built upon Conservative Q-Learning (CQL). However, CQL-based approaches suffer from two fundamental limitations: (1) the Markov assumption fails to capture the strong non-Markovian temporal dependencies inherent in real-world user behaviors, and (2) TD learning with bootstrapping incurs severe cumulative errors and credit assignment difficulties under delayed rewards, particularly in long-horizon settings where users enter the app multiple times daily. To address these limitations, we propose GLAN (Generative Landing-page Adaptive Navigator), a sequence modeling framework built on Decision Transformer to tackle PLPM from a unified global-local perspective. Specifically, GLAN incorporates two key modules. First, we design the L-RTG module that captures users' inter-day consumption dynamics to provide accurate global guidance for all page assignments within a day. Furthermore, we propose the HRM module that decomposes session-level feedback into fine-grained signals, enabling precise local supervision for each page assignment. Extensive online experiments conducted on the Kuaishou platform demonstrate the effectiveness of GLAN, achieving +0.158\% and +0.108\% improvements on Daily Active Users (DAU) and user Lifetime (LT) respectively.

cs.IR↗

arXiv2026

Covariate-adjusted win statistics in randomized clinical trials with ordinal outcomes

Ordinal outcomes are common in clinical settings where they often represent increasing levels of disease progression or different levels of functional impairment. In this article, we focus on representing the average treatment effect for ordinal outcomes via intrinsic pairwise outcome comparisons captured through win estimands, such as the win ratio and win difference. Recognizing the value of baseline covariate adjustment toward enhanced precision, we first develop propensity score weighting estimators, including both inverse probability weighting (IPW) and overlap weighting (OW), tailored to estimating win estimands. Furthermore, we develop augmented weighting estimators that leverage an additional ordinal outcome regression to potentially improve efficiency over weighting alone. Leveraging the theory of U-statistics, we establish the asymptotic theory for all estimators, and derive closed-form variance estimators to support statistical inference. We also prove that all of the covariate-adjusted estimators do not compromise consistency for the target estimand even when the associated working models are incorrectly specified; hence these covariate-adjusted estimators are model-robust. Through simulations we demonstrate the enhanced efficiency of the weighted estimators over the unadjusted estimator, with the augmented weighting estimators showing a further improvement in efficiency except for extreme cases. Finally, we illustrate our proposed methods with the ORCHID trial, and implement our covariate adjustment methods in an R package winPSW.

stat.ME↗

arXiv2026

Sensitivity analysis for causal mediation: bridge score, sharp sensitivity bounds, and calibration

Causal mediation analysis decomposes the total treatment effect into a portion operating through a hypothesized mediator and a residual direct portion. Identification of natural direct and indirect effects typically rests on the mediator stage of sequential ignorability, which cannot be empirically verified and requires explicit sensitivity analysis. We formulate the \emph{bridge score}, a mediator-stage balancing score, as a low-dimensional vector formed from the two treatment-specific mediator densities at a common mediator value, and show that it balances baseline covariates for the mediator stage relevant to natural effect identification. Conditional on the bridge score, we derive a sharp pointwise variance envelope on the unidentified mediator-outcome confounding function in terms of latent outcome relevance and residual selection. To make the bound operational for sensitivity analysis, we further introduce a residual budget calibration approach based on local residual outcome variation and record a complementary range bound for support-based restrictions. Finally, we show how the pointwise bound can be operationalized for inference through a scalar functional reduction and a Bayesian g-computation algorithm that combines observed-data posterior uncertainty with user-specified sensitivity uncertainty, rather than treating the unidentified sensitivity corrections as learned from the likelihood.

stat.ME↗