arXiv subjects

Wen Li

Publications and source records attributed to Wen Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Beyond Source: An Empirical Study of Python Bytecode Security Risks

Python package security is largely source-centric, yet Python runtimes can execute bytecode directly through .pyc files, compiled-only modules, and marshalled code objects, creating an inspection-execution gap. We present an empirical study of Python bytecode as a security artifact. We measure bytecode exposure in PyPI distributions, evaluate practical analyzability using version-aware tooling, assess CPython runtime robustness under adversarial bytecode, and test source-level reproduction of bytecode findings. Across 1,034,843 collected PyPI artifacts, we identify 7,388 bytecode-containing artifacts, including 228,578 .pyc files and 28,193 artifact-local source-less .pyc files. For modern CPython 3.8-3.14 bytecode, at least one selected decompiler emits source for 204,901 of 204,904 in-scope files, a result measuring emission rather than verified functional equivalence. Tools are non-robust: observed PyPI bytecode triggers managed-code exceptions and timeouts, while adversarial mutated bytecode also drives decompilers into native process failures; together these outcomes yield 17 distinct robustness signatures. Fuzzing produces 1,009 stack-deduplicated runtime findings dominated by pointer-dereference symptoms; 261 groups exhibit potential memory-corruption characteristics, and at least 91.7% of groups reach execution beyond the documented-unsafe ingestion boundary. None reproduce from ordinary Python source. Bytecode is thus a visible ecosystem artifact, a practical analysis target, and a security-relevant interpreter input whose behavior need not match source-level behavior.

cs.CR↗

arXiv2026

Dissecting Software Graphs: Structural Insights for Driver-Guided Fuzzing

Many software systems expose multiple execution modes through command-line options, subcommands, and configuration flags. For such programs, fuzzing depends on both mutated inputs and the invoked mode. Yet evaluations still focus on coverage and bug counts, leaving unclear how execution modes partition, overlap, and miss software structure, and how these differences affect effectiveness. We present an empirical study of software structure under multi-driver fuzzing. We propose a structural abstraction that uses a static call graph as a shared backbone and projects driver-specific dynamic coverage onto it to derive driver-induced subgraphs. Based on this abstraction, we develop a four-phase methodology for backbone construction, fuzzing and profiling, graph-based analysis, and research-question-driven evaluation. We apply it to 27 OSS-Fuzz-derived C/C++ projects, spanning 43 executables and 854 driver configurations. Under the same total budget, multi-driver fuzzing outperforms the best single-driver baseline, increasing covered call-graph nodes by 27.9% and CFG-edge coverage by 73.5%, and revealing 11 unique bugs and abnormal behaviors largely missed by single-driver fuzzing. However, driver contributions are uneven, subgraphs differ substantially in cohesion, fragmentation, modularity, overlap, and residual under-exploration follows recurring regimes rather than a homogeneous tail. These results show that multi-driver fuzzing is fundamentally a structural exploration problem.

cs.SE↗

arXiv2026

Near-Unity Excitation and Radiative Efficiencies in Electroluminescence Without External Carrier Injection

Electroluminescence occurring without external charge injection is typically characterized by weak emission and excessive driving voltage, due to low excitation and radiative recombination efficiencies. Here, we demonstrate non-injecting electroluminescence (NI-EL) that challenges this conventional perception. To achieve this, we introduce an operational paradigm that leverages remote, state-abundant charge reservoirs, which elevates the excitation efficiency close to unity - a greater-than-20-fold improvement over the benchmark. This strategy is augmented by quantum dots (QDs) with nonmonotonically graded shells, raising the high-field radiative efficiency by approximately 7-8-fold. The resultant RGB NI-EL devices uniformly exhibit bright and efficient pulsed emissions, with key metrics including: a turn-on threshold of 3.7 Vrms for red; a luminance of 291,628 nits and a power efficiency of 302.6 lm/W for green, with light-outcoupling enhancement; and, for blue, the superior emitter stability of the first QD-based blue NI-EL over its light-emitting diode counterpart. The minimal dielectric loss, sub-100 ns response time, and external EL efficiency of up to 45.4% further reinforce the mechanism-performance causality. These results overcome the inherent mechanistic limitations of NI-EL and establish performance that rivals or surpasses injection-type EL, including AC- or DC-driven variants, positioning NI-EL as a promising platform for high-performance pulsed light sources.

physics.optics↗

arXiv2026

UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillation

Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating the need for access to the original training dataset. Existing DFKD methods rely heavily on architecture-specific statistical priors (e.g., Batch Normalization statistics) to guide data synthesis, however, such architecture-dependent priors are often absent in modern architectures such as Vision Transformers (ViTs), resulting in degraded semantic quality of the synthesized data and consequently catastrophic performance degradation. In this paper, we propose \emph{UniDFKD}, a unified data-free knowledge distillation framework that replaces architecture-specific statistics with explicit, architecture-agnostic semantic priors. \emph{UniDFKD} governs the entire synthesis-distillation pipeline along three dimensions: (1) Categorical Semantic Conditioning (CSC) defines \emph{what} to synthesize by persistently modulating the generator with language-derived embeddings to capture semantic diversity; (2) Spatial Semantic Anchoring (SSA) dictates \emph{where} evidence belongs by anchoring the teacher's spatial attributions to a Gaussian prior; and (3) Spatial Semantic Distillation (SSD) controls \emph{how} knowledge is transferred by explicitly aligning teacher-student spatial evidence alongside predictions. Extensive experiments across CNNs and ViTs demonstrate that UniDFKD establishes a new state-of-the-art, outperforming existing methods by an average absolute margin of over 20\% in both homogeneous and heterogeneous settings.

cs.CV↗

arXiv2026

The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents

GUI agents are commonly trained offline from successful interaction trajectories. Standard training decomposes each trajectory into prefix-action pairs: the agent predicts an action from the current screen and interaction history, while the subsequent observation is discarded. This removes the rationale of why an action is correct: the evidence often appears only on the subsequent screen. For example, to enable Soft Wrap, the agent should click Edit or View, but nothing reveals this until the menu opens. Without such evidence, standard imitation gives the model little chance of ever sampling and thus learning the correct reasoning. To address this issue, we propose Gated Hindsight Distillation (GHD), which uses the next screenshot as privileged information during training. A student predicts from the observable trajectory prefix, while a parameter-sharing teacher additionally observes the next screenshot and re-scores the student's on-policy responses. We apply distillation only when the student fails and the hindsight-conditioned teacher recovers the demonstrated action. GHD improves task success over GRPO on AndroidWorld and AndroidLab across two vision-language models. The code and checkpoints will be made available.

cs.CV↗

arXiv2026

Electrotactile Improves Thermal Referral

Thermal referral enables thermal sensations in locations lacking thermal actuators--this is achieved using vibrotactile actuators to redirect a nearby thermal sensation to where a tactile sensation is applied. However, we found that its reliance on vibration introduces critical limitations: it struggles to produce cold referral, and the inherent strong tactile "buzz" makes it unsuitable for simulating non-contact thermal events, such as the chill of an open freezer in VR (in contrast to contact-based thermal events like touching the freezer's cold handle). To improve this, we propose a shift from vibrotactile to electrotactile-based thermal referral. We evaluated in two user studies--a psychophysics experiment (N=22) and a VR deployment (N=20)--where we contrasted electrotactile with vibrotactile-based thermal referral. Our results reveal key advantages of the electrotactile based thermal referral: (1) increases the referral rate for cold sensations; (2) increases thermal perception while minimizing tactile; and (3) improves realism across a range of VR thermal scenarios, specifically distinguishing between contact-based and non-contact thermal events. Finally, we provide design guidelines for choosing tactile cues to create immersive multimodal thermal experiences in VR.

cs.HC↗

arXiv2026

OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation

This paper introduces OmniMotion-X, a versatile multimodal framework for whole-body human motion generation, leveraging an autoregressive diffusion transformer in a unified sequence-to-sequence manner. OmniMotion-X efficiently supports diverse multimodal tasks, including text-to-motion, music-to-dance, speech-to-gesture, and global spatial-temporal control scenarios (e.g., motion prediction, in-betweening, completion, and joint/trajectory-guided synthesis), as well as flexible combinations of these tasks. Specifically, we propose the use of reference motion as a novel conditioning signal, substantially enhancing the consistency of generated content, style, and temporal dynamics crucial for realistic animations. To handle multimodal conflicts, we introduce a progressive weak-to-strong mixed-condition training strategy. To enable high-quality multimodal training, we construct OmniMoCap-X, the largest unified multimodal motion dataset to date, integrating 28 publicly available MoCap sources across 10 distinct tasks, standardized to the SMPL-X format at 30 fps. To ensure detailed and consistent annotations, we render sequences into videos and use GPT-4o to automatically generate structured and hierarchical captions, capturing both low-level actions and high-level semantics. Extensive experimental evaluations confirm that OmniMotion-X significantly surpasses existing methods, demonstrating state-of-the-art performance across multiple multimodal tasks and enabling the interactive generation of realistic, coherent, and controllable long-duration motions.

cs.CV↗

arXiv2026

CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation

3D unsupervised domain adaptive (UDA) segmentation mitigates the high cost of manual annotations of the new domain data. Self-training has emerged as the dominant approach in this area, where its success heavily depends on a well-initialized warm-up model to generate reliable pseudo labels. However, existing methods often depend on source supervision or output-level adversarial alignment to obtain the warm-up model, which suffer from limited generalization and training instability due to the large domain gap between domains. Constructing domain-similar representations is an effective way to bridge this gap. In this work, we propose CVKD-UDA, which revisits voxel size as a core design factor to construct domain-similar representations and leverages cross-view complementary cues to balance transferability and discriminability of the warm-up model. First, we generate two complementary views by varying voxel sizes and introduce a cross-view knowledge distillation (CVKD) to enhance generalization and target perception of the model. Second, to balance transferability and discriminability, we design a lightweight Decouple-Adapter and an auxiliary imitation classifier to decouple cross-view knowledge transfer. Extensive experiments on two benchmarks demonstrate that CVKD-UDA effectively improves the performance of self-training methods and provides a new perspective for 3D UDA segmentation. Our code will be available at GitHub.

cs.CV↗

arXiv2026

Structured Evidence Selection for Weakly Supervised Video Anomaly Detection

Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit large variations in appearance and temporal duration, while scene appearance and action dynamics are often tightly entangled. Consequently, existing models tend to rely on scene-related statistical cues rather than true behavioral deviations, resulting in unstable detection performance. To address this challenge, we propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process over clip-level visual evidence. Instead of directly mapping aggregated features to anomaly scores, SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints. This mechanism adaptively emphasizes anomaly-relevant semantics while suppressing scene interference, thereby alleviating semantic entanglement under weak supervision. Furthermore, we introduce a lightweight geometric discrimination module that constructs a dual-prototype structure in the embedding space, enabling anomaly decisions through relative geometric relations. Extensive experiments on UBnormal, ShanghaiTech, and UCF-Crime show that SESAD achieves 67.92, 97.99, and 88.46 AUC, respectively, while maintaining high computational efficiency and overall consistently stable anomaly discrimination.

cs.CV↗

arXiv2026

Evolution of Linear Perturbations under Time-Dependent Hubble Friction I: SR-USR-SR Inflation

The origin of the finite dip in the curvature power spectrum of instantaneous Slow-Roll (SR)-Ulta-Slow-Roll (USR)-SR inflation remains controversial at linear order, and its full spectral features still lack a complete asymptotic analytical description. We revisit linear perturbation dynamics in this framework. Using the junction method and asymptotic expansions of Hankel functions, we for the first time derive accurate and simple asymptotic expressions for mode evolution and the resulting power spectrum, based on three systematic rules for dominant-term identification across transitions. We find the finite dip arises from cancellation between two growing modes within linear perturbation theory, rather than between constant and growing terms as previously suggested. We also provide analytical descriptions of the amplitude enhancement and the two oscillatory patterns observed in the spectrum. All asypmtotic analytical results are validated by numerical calculations with the reconstructed SR-USR-SR inflationary potential.

gr-qc↗

arXiv2026

GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine

Reasoning segmentation requires localizing targets based on complex, implicit queries. Current end-to-end models typically entangle perception and deduction into an opaque black box, severely limiting interpretability and scalability. To address this, we propose GEAR-Seg (Grounded Explainable Agent for Reasoning Segmentation), an explicitly decoupled agent that shifts the paradigm by translating visual pixels into dense, attribute-rich text. By decoupling class-agnostic segmentation, semantic description, and Large Language Model (LLM) deduction, GEAR-Seg transforms implicit reasoning into an explicit, trackable logic chain. As a zero-shot inference framework, it achieves highly competitive performance across diverse reasoning and fine-grained referring segmentation benchmarks. Furthermore, GEAR-Seg inherently functions as a highly scalable data engine. Utilizing this engine, we construct GEAR-131K, a massive benchmark (over 38k images, 656k QA-mask pairs) introducing a multifaceted taxonomy tailored for complex real-world manipulation-oriented reasoning. Finally, distillation experiments demonstrate that lightweight models supervised exclusively by our automated pipeline closely match the upper-bound performance of costly human-annotated baselines.

cs.CV↗

arXiv2026

SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios

Homography estimation, as one of the fundamental problems in computer vision, remains challenged by scale variation scenarios where image pairs potentially exhibit significant scale discrepancies. Existing deep learning frameworks frequently suffer from a significant performance degradation in such cases, as they rely on limited displacement assumptions and local feature consistency that might not hold under large scale gaps. In this paper, we propose SA-Homo, a novel scale-adaptive homography estimation framework designed to achieve robust alignment across a wide range of scale discrepancy ratios. We adopt a hierarchical scale alignment strategy that transitions from the global perspective with a heavy module to a local perspective with a light module. Specifically, we introduce the Scale-aware Discrepancy Bridging Module (SDBM) for initial alignment, which utilizes a Multi-scale Linear Attention Cascade (MLAC) to capture long-range dependencies and mitigate feature inconsistencies, along with a global Cross-scale Similarity Matrix Block (CSMB) for scale robust correlation representation. Once the initial scale gap is bridged, a lightweight Iterative Homography Estimation Refinement Module (IHERM) progressively polishes the result using local correlations. To facilitate this research, we contribute the HMSA dataset, a high-resolution, multi-modal satellite benchmark specifically tailored for scale-variant challenges. Extensive experiments demonstrate that SA-Homo maintains high precision even under 8$\times$ scale discrepancies, outperforming state-of-the-art methods in both conventional scale-similar scenarios and challenging scale variation scenarios. Code and collected datasets are available at https://github.com/shangxuanx330/SA_Homo

cs.CV↗

arXiv2026

Agentic Collaborative Cognition for Zero-Shot 3D Understanding

Recent advancements have explored agentic zero-shot 3D understanding by reformulating it as video keyframe understanding with Multimodal Large Language Models (MLLMs). However, existing methods face an intrinsic bottleneck due to the finite observation perspectives inherent in videos and the implicit perception of 3D scenes. In this paper, we propose a collaborative multi-agent framework that assigns a Planning Agent to handle high-level viewpoint planning and supplement novel perspectives, and a Perception Agent to explicitly summarize the 3D scene into a structured holistic cognitive map. Specifically, Planning Agent first analyzes this cognitive map to determine query-relevant viewpoints and supplements missing critical perspectives to ensure comprehensive observation. Subsequently, Perception Agent documents object-level attributes from these views by assigning consistent instance identifiers across viewpoints, thereby integrating fragmented observations into the holistic cognitive map. In parallel, it provides feedback to filter out mismatched candidate objects and guide subsequent viewpoint planning. Through this closed-loop iterative process, two agents collaboratively figure out candidates until Perception Agent determines that sufficient information has been captured to complete the task. Extensive experiments demonstrate that our method achieves state-of-the-art performance on 6 benchmarks, with improvements of 11.1\% Acc@0.5 on ScanRefer, 14.6 BLEU-1 on 3D-assisted dialog, and 2.1 EM on SQA3D.

cs.CV↗

arXiv2026

NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction

Reconstructing continuous speech from scalp electroencephalography (EEG) remains fundamentally challenging. EEG provides a weak, spatially diffuse, and highly variable measurement of distributed cortical activity, whereas speech is organized as a coherent acoustic trajectory with strong harmonic and temporal structure. The resulting mismatch makes waveform regression unstable and causes stochastic multi-step generation to be sensitive to artifact-dependent conditioning and subject variability. We introduce NeuroSonic, a conditional flow-matching framework for EEG-to-speech reconstruction. Instead of predicting waveforms directly or refining them through stochastic denoising, NeuroSonic learns a deterministic probability-flow velocity field that transports a noise-corrupted acoustic state toward clean speech under EEG conditioning. EEG and audio are embedded into a shared token space and processed by a time-conditioned gated Transformer that parameterizes the transport ordinary differential equation. This formulation models trajectory evolution explicitly while avoiding iterative stochastic sampling. We evaluate NeuroSonic on the CineBrain and EAV benchmarks under cross-subject evaluation. Across both datasets, the proposed method improves distributional realism, spectral fidelity, and perceptual quality over representative GAN-, diffusion-, and mean-flow baselines, with up to a 26.3\% gain in overall perceptual quality. The performance gap is most evident in artifact-heavy segments, where conditioning variability is strongest. These findings indicate that deterministic conditional transport provides a stable and effective formulation for EEG-driven speech reconstruction. Code is available at https://github.com/Y-Research-SBU/NeuroSonic/ .

cs.LG↗

arXiv2026

Investigating the Uncertainty of Cellular Microenvironment Parameter Estimations via Diffusion MRI Cytometry

This study aims to identify cell microenvironment parameters that can be robustly estimated from IMPULSED diffusion MRI signals and to develop a reliable mapping-based estimation framework. Diffusion MRI signals were simulated using the established IMPULSED model with one pulsed gradient spin echo sequence and two oscillating gradient spin echo sequences at different frequencies. Five cellular parameters were considered: cell diameter ($d$), intracellular diffusion coefficient ($D_{in}$), intracellular volume fraction ($V_{in}$), extracellular diffusion coefficient ($D_{ex}$), and the frequency-dependent slope of $D_{ex}$ ($β_{ex}$). Parameter uncertainty was quantified using Jacobian-based sensitivity analysis at an SNR of 30, representing clinically achievable conditions on a 1.5T MRI scanner. To enable direct parameter mapping, signals were logarithmically transformed, reduced in dimension using principal component analysis, and then used to estimate parameters with linear regression, fourth-order polynomial regression, and a fully connected four-layer neural network. Model validation was performed in vitro using MC38 cell lines. Uncertainty analysis identified $d$, $V_{in}$, and $D_{ex}$ as robustly derivable parameters, each with relative uncertainty below 1.0. Among the tested models, the four-layer neural network performed best, with mean absolute errors of 1.7 $μ$m for $d$, 5.06% for $V_{in}$, and 0.28 $μ$m$^2$/ms for $D_{ex}$. In vitro validation showed a 6.7% error in cell diameter estimation. These results demonstrate that IMPULSED dMRI can support robust estimation of key cell microenvironment parameters and provide a practical framework for noninvasive assessment of tumor microenvironment changes during radiation therapy response monitoring.

physics.med-ph↗

arXiv2026

ResCLIP: Residual Attention for Training-free Dense Vision-language Inference

While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such deficiency in dense predictions to the self-attention layers in the final block, and have achieved commendable results by modifying the original query-key attention to self-correlation attention, (e.g., query-query and key-key attention). However, these methods overlook the cross-correlation attention (query-key) properties, which capture the rich spatial correspondence. In this paper, we reveal that the cross-correlation of the self-attention in CLIP's non-final layers also exhibits localization properties. Therefore, we propose the Residual Cross-correlation Self-attention (RCS) module, which leverages the cross-correlation self-attention from intermediate layers to remold the attention in the final block. The RCS module effectively reorganizes spatial information, unleashing the localization potential within CLIP for dense vision-language inference. Furthermore, to enhance the focus on regions of the same categories and local consistency, we propose the Semantic Feedback Refinement (SFR) module, which utilizes semantic segmentation maps to further adjust the attention scores. By integrating these two strategies, our method, termed ResCLIP, can be easily incorporated into existing approaches as a plug-and-play module, significantly boosting their performance in dense vision-language inference. Extensive experiments across multiple standard benchmarks demonstrate that our method surpasses state-of-the-art training-free methods, validating the effectiveness of the proposed approach. Code is available at https://github.com/yvhangyang/ResCLIP.

cs.CV↗

arXiv2026

Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention

Retinal vessel segmentation is crucial for diagnosis and assessment of ocular diseases. Notably, segmentation of small retinal vessels has been consistently recognized as a challenging and complex task. To tackle this challenge, we design a hybrid CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels. Considering that the traditional mamba architecture with horizontal-vertical scanning may compromise the topological integrity of target structures and result in local discontinuities in small retinal vessels, we present a polygon scanning visual state space model (PS-VSS) to identify small vessel structural features by multi-layer reverse scanning way. Which effectively preserves pixels connectivity, thereby substantially mitigating the loss of information pertaining to small vessels. Furthermore, as we all known that the spatial domain prioritizes positional and structural information, while the frequency domain emphasizes global perception and local detail components, a space-frequency collaborative attention mechanism (SFCAM) is introduced within the skip connection to extract efficient features from the spatial and frequency domains. This strategy empowers the model to dynamically enhance the key features while effectively suppressing clutters. To assess the efficacy of our model, it was tested on three publicly available datasets: DRIVE, STARE, and CHASE_DB1. Compared to manual annotations, our model demonstrated F1 scores of 0.8283, 0.8282, and 0.8251, Area Under Curve (AUC) values of 0.9806, 0.9840, and 0.9866, and Sensitivity (SE) values of of 0.8268, 0.8314, and 0.8484 across three datasets, respectively. The effectiveness of our model was validated through both visual inspection and quantitative analysis.

cs.CV↗

arXiv2026

Let EEG Models Learn EEG

High-fidelity EEG generation is critical for alleviating data scarcity and addressing privacy constraints in large-scale neural modeling. Despite recent progress, most existing approaches formulate EEG generation via discrete denoising objectives, which inadequately reflect the inherently continuous temporal dynamics and spectral structure of neural activity. As a result, these methods often struggle to preserve long-range temporal dependencies and exhibit mismatches in the spectral and temporal structure of the generated signals. In this work, we argue that effective EEG generation requires models that operate directly on the continuous evolution of neural signals. We introduce Just EEG Transformer (JET), a generative framework based on conditional flow matching that models EEG as raw sequences evolving along continuous trajectories. By learning a smooth vector field that transports noise to the EEG data distribution, JET captures temporal continuity and transient dynamics without relying on discretized denoising schemes or domain-specific representations. To ensure that the learned dynamics remain consistent with key properties of EEG signals, we introduce principled constraints that preserve spectral structure, temporal stationarity, and signal-level statistics. Across three large-scale benchmarks, JET consistently achieves state-of-the-art performance, reducing TS-FID by over 40% compared to strong baselines. Extensive analyses show that JET captures key structural properties of neural dynamics, providing a scalable and principled approach to EEG generation. Project page: https://y-research-sbu.github.io/JET/ .

cs.CV↗