arXiv subjects

Lu Zhang

Publications and source records attributed to Lu Zhang.

At least 19 recordsLinked to original sources

arXiv2026

OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models

While Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse tasks, they suffer from hallucinations where generated outputs contradict or misrepresent input semantics. Existing research typically addresses hallucination detection within a single modality or task type, limiting generalizability. We introduce OmniHallu, a unified hallucination detection framework spanning both comprehension and generation tasks across image, video, and audio modalities. We contribute OmniHallu-Bench, a 10,000-sample benchmark with claim-level human annotations covering six cross-modal tasks: image-to-text (I2T), video-to-text (V2T), audio-to-text (A2T), text-to-image (T2I), text-to-video (T2V), and text-to-audio (T2A). Our multi-agent architecture decomposes model outputs into atomic claims, verifies them through modality-specific experts, and aggregates evidence via structured reasoning. We further propose a preference-optimized trainable verifier that approximates the multi-agent decision boundary, reducing expert calls by 66% with minimal performance loss. Extensive experiments reveal a consistent modality-dependent performance gradient and provide fine-grained insights into cross-modal hallucination patterns.

cs.CL↗

arXiv2026

Efficient Fairness Auditing Across Guidance Scales in Text-to-Image Diffusion Models via Causal Abstraction

Fairness auditing of text-to-image diffusion models often requires generating large numbers of images across sampling configurations, making comprehensive evaluation computationally expensive. We propose a causal-abstraction-based audit instrument for efficiently evaluating fairness under interventions on the classifier-free guidance scale. Given a fixed prompt and a target feature function, we represent the diffusion process as a low-level structural causal model and construct a corresponding high-level model over abstract denoising states. We characterize the projected causal structure, establish identifiability of the fairness-relevant interventional query, and provide sufficient conditions under which the high-level model preserves this query. A probabilistic transformer implements the high-level model as an amortized predictor of target-feature distributions across guidance scales. Experiments evaluate distributional fidelity, fairness-query accuracy, and computational efficiency. We present two auditing demonstrations: one using standard Stable Diffusion 1.5 and another using StayFair, a fairness-enhanced Stable Diffusion model, to examine their behavior across guidance scales.

cs.LG↗

arXiv2026

Core-Level Spectroscopy Decodes Bond-Alternation Dynamics of Cyclo[18]Carbon

The advent of X-ray free-electron lasers and high-harmonic generation has made time-resolved X-ray spectroscopy a powerful tool for probing local atomic environments, yet whether localized core excitations can report on global collective distortions remains open. Cyclo[18]carbon (C$_{18}$), with its polyynic ground state (D$_\text{9h}$) and cumulenic transition state (D$_\text{18h}$), provides an ideal model to address this long-standing issue in bond-length alternation (BLA) dynamics. Mapping two-dimensional potential energy surfaces by first-principles simulations, we find that core ionization symmetrizes the ground-state double-well potential along the BLA coordinate. Our calculated X-ray spectra reveal remarkable sensitivity to bond-length variations: C1s ionization potentials vary by up to 2.4~eV across the BLA coordinate (1.1--1.4~\AA), with a 0.9~eV variation for minima predicted by different functionals, while NEXAFS $\pi^*$ peaks shift by up to 4~eV across the same coordinate. These predicted signatures provide a quantitative spectroscopy--structure dictionary for decoding transient structures in future ultrafast X-ray experiments and monitoring bond-alternation dynamics in real time.

physics.atm-clus↗

arXiv2026

Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agriculture Platform in Hainan

Smart agriculture platforms are widely regarded as key carriers for implementing China's pesticide and fertilizer reduction, water-saving and carbon-reduction agendas, yet a unified quantitative framework for assessing their green value is still lacking. Taking an AI-driven decision platform for tropical agriculture as the object (integrating large-language-model question answering, multimodal pest diagnosis, IoT sensing, satellite remote sensing, and a closed-loop field record system), this study builds a cradle-to-farm-gate agricultural carbon accounting model covering pesticide and fertilizer production, field N2O, irrigation electricity and paddy CH4, translates platform interventions into quantifiable transmission parameters, and propagates parameter uncertainty by Monte Carlo simulation over three Hainan scenarios (mango, winter vegetable, rice/nanfan, area-weighted 40%:30%:30%). Under full adoption, median reductions are 23.5% (90% interval 15.0%-33.2%) for pesticide use, 21.0% (13.8%-28.9%) for fertilizer, 16.5% (10.9%-23.5%) for irrigation water, and 21.5% (16.1%-27.2%) for carbon intensity. Attainment probabilities are high for fertilizer reduction >=15% (90.6%) and clear carbon decline (98.1%), but only about 20% for aggregate water saving >=20%, favoring scenario-specific statements. Sobol first-order indices show soil-test recommendation and organic substitution jointly explain about 83% of the variance of aggregate carbon-intensity reduction. Convergence tests show 10,000 iterations stabilize all statistics; conservative/baseline/optimistic scenario bounds are reported. The framework offers a reproducible, calibration-ready methodology for ex-ante green-value assessment and pilot observation design.

cs.AI↗

arXiv2026

Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform: Evidence from Two Monte Carlo Experiments

Smart agriculture platforms usually bundle AI diagnosis, IoT sensing and decision push into a single package, so the green benefit attributable to each component remains unclear and resource-allocation decisions lack quantitative evidence. Building on a previous platform-level Monte Carlo assessment, this paper makes the components explicit and runs two controlled simulation experiments. Experiment 1 follows the chain from AI capability to farmer behavior to agrochemical input reduction, modeling pesticide/fertilizer reduction as avoidable blind-application share times prescription effectiveness times decision-touch coverage times adoption rate, and compares an experienced-extension mode with the AI mode: the probability of reaching 20% pesticide reduction is essentially zero in the extension mode but 20.7% at baseline, up to 49% with diagnosis accuracy 0.95 and adoption 0.85 under AI; the probability of 15% fertilizer reduction rises from near zero to 52.0%. Experiment 2 compares current practice (P0), IoT engineering retrofit (P1), and P1 plus AI irrigation scheduling (P2): median aggregate water saving rises from 7.8% (P0) to 11.0% (P1) and 16.0% (P2), with AI adding 5.0 percentage points beyond engineering; paddy CH4 reduction reaches 30.5% under AI scheduling versus 19.8% under manual operation, and the rice irrigation-methane subsystem carbon intensity declines 27.9%. Sensitivity analyses of both experiments consistently indicate that the primary bottleneck for meeting green targets is farmer adoption rather than algorithm accuracy, and that AI data fusion is robust to soil-moisture sensing errors. This work provides a reproducible simulation framework for component-level green-value evaluation and promotion-strategy optimization of smart agriculture platforms.

cs.AI↗

arXiv2026

LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models

Vision-Language-Action (VLA) or World Action (WAM) models have recently demonstrated remarkable performance in robotic manipulation. On LIBERO, SOTA method have achieved nearly 100\% success rates, seemingly suggesting that the models are ready for deployment in real world. However, near perfect performance on existing benchmarks can be misleading: success under ideal conditions does not imply real world robustness. Existing benchmarks primarily evaluate task completion from predefined initial states, while real world interactions inevitably involve failures such as failed grasps, collisions, and unintended object movements. A robot must therefore not only execute tasks successfully, but also recognize and recover from failures to continue the task. Yet this capability remains largely unmeasured, revealing a critical gap between benchmark performance and real world reliability. To address this gap, we introduce LIBERO-Recover Benchmark, a large scale benchmark for failure recovery in robotic manipulation. Built upon LIBERO, we collect real execution failures from SOTA embodied models and construct 1,000+ scenarios across four recovery levels: (1) Action Retry, (2) Action Adaptation, (3) Object State Recovery, and (4) Environmental Recovery. We evaluate four core capabilities: spatial understanding, object structure reasoning, interaction understanding, and topological reasoning. As the first large-scale benchmark for embodied failure recovery, LIBERO-Recover shifts evaluation from \emph{Can the robot succeed?''} to \emph{Can the robot recover after failure?''}, promoting robust and generalizable embodied agents. The project will be avaible in \textcolor{blue}{https://liulin815.github.io/LIBERO-Recovery/}.

cs.RO↗

arXiv2026

From multi-layered problems to multiple two-layered problems: a novel frequency-time hybrid multiple-scattering integral equation solver

This paper proposes a novel frequency-time hybrid multiple scattering (FTH-MS) integral equation solver for time-dependent wave equation problems in general multi-layered media, with remarkable scalability with respect to the number of layers $N$. In light of the finite speed of wave propagation, the new methodology provides an innovative multiple-scattering idea of re-modeling the original $N$-layered problem into a sequence of $N-1$ two-layered sub-problems, for which the main advantages lie in that (i) each sub-problem enjoys much simpler wave scattering properties compared with the complicated problem in a multi-layered medium, (ii) it enables to develop high-accuracy solver utilizing Fourier transform and frequency-domain boundary integral equation (BIE) method; and (iii) numerical evaluation of the sub-problems in each multiple scattering step can be parallelized. Both multiplicative- and additive-type strategies are developed and equivalence results, which indicate that the $M$-th order multiple scattering sums can provide equivalent representations of the solutions up to a certain time $T(M)$, are rigorously derived. Owing to the existed result of exponential convergence of the perfectly-matched-layer (PML) truncation for two-layered problem, all the sub-problems is numerically resolved by means of the FTH method based on the Fourier transform and the PML-BIE method whose numerical evaluation is addressed utilizing the Chebyshev-based rectangular-polar solver with high accuracy. Numerical examples are presented to validate the efficiency and accuracy of the proposed method.

math.NA↗

arXiv2026

MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding

Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling increases compute cost and inference latency. Mixture-of-Experts (MoE) architectures offer a compelling alternative, having enabled efficient scaling in LLMs, yet the MoE design space for CLIP-style vision encoders remains underexplored at State-of-the-Art (SOTA) levels. In this work, we systematically study MoE designs for vision encoder scaling and find that fine-grained MoE topologies yield substantial gains over both dense and standard MoE counterparts. We further propose an auxiliary-loss-free balancing variant for better expert utilization, and design a specialized MoE kernel to mitigate inference latency overhead. To enhance video capabilities while preserving image knowledge, we introduce frame-level distillation paired with a novel freezing mechanism. We pretrain a series of Mixture-of-Experts Vision Encoders (MoE-ViE) across a range of sizes, all consistently outperforming their dense counterparts. Our largest model matches the zero-shot performance of a SOTA encoder 1.7x its size at 76% of its latency. When aligned with an LLM, MoE-ViE surpasses all compared encoders on image and video benchmarks, including those with up to 5x more activated parameters. Code is available at https://github.com/facebookresearch/moe_vie.

cs.CV↗

arXiv2026

PushDualGen: Enabling LLMs to Generate Semantic IDs with Interpretable Copy for Industrial Push Recommendation

Push recommendation in KuaiShou proactively delivers personalized content to nearly one billion users to facilitate their engagement. Recently, generative recommendation has achieved end-to-end user personalization through semantic ID. However, their black- box characteristics make recommendation logics difficult to trace, hindering their deployment. OneRec-Thinking addresses this by incorporating CoT before generating SIDs, but this significantly increases inference cost. To support large-scale industrial applications, we propose PushDualGen, a lightweight generator, which first generates the SID and then produces a copy as a skippable explanation. PushDualGen has been deployed in Kuaishou's push recommendation system. Online A/B tests demonstrate the effectiveness of PushDualGen, delivering significant improvements in both user attraction and satisfaction. The effective play rate for videos recommended to users has relatively increased by 8.50%, while the dissatisfaction rate has relatively fallen by 37.70%. In the long term, PushDualGen optimises the content ecosystem, providing more exposure for long-tail videos.

cs.IR↗

arXiv2026

ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Models

LiDAR-based collaborative 3D perception in Vehicle-to-Everything (V2X) systems typically relies on fusing bird's-eye-view (BEV) features across agents. However, current BEV representations, typically extracted by LiDAR backbones trained from scratch, are geometry-dominated and lack general semantic priors, inherently limiting the efficacy of feature-level collaboration. Meanwhile, vision foundation models (VFMs) pretrained on large-scale image data have demonstrated strong capability in learning general-purpose and informative visual representations for 2D tasks, and have the potential to enhance agent-wise LiDAR BEV representations for collaboration. Despite this potential, adapting VFMs to LiDAR-based 3D detection remains challenging due to the substantial image-point cloud modality gap. To bridge this gap, we propose ViCo3D, a collaborative 3D object detection framework powered by VFMs. Specifically, ViCo3D adapts VFMs to LiDAR-based collaborative perception from three aspects: First, ViCo3D projects point clouds onto the BEV plane as three-channel images, enabling DINOv2 to extract BEV-space visual features from LiDAR inputs. Besides, to effectively integrate these DINOv2-derived features with LiDAR geometric features, ViCo3D introduces a multi-scale BEV fusion module within the single-agent encoder. In addition, ViCo3D adopts an ego-centric cross-agent fusion strategy to aggregate complementary information from multiple agents. Experiments on DAIR-V2X and V2XSet demonstrate that ViCo3D achieves state-of-the-art 3D detection performance. Remarkably, it delivers up to 1.8x greater collaborative gains than prior methods on DAIR-V2X. The code will be made public available for future investigation.

cs.CV↗

arXiv2026

$\mathfrak{so}_n(\mathbb{C})$-modules which are free over an abelian nilradical

In this paper, we classify the category of $\mathfrak{so}_n(\mathbb{C})$-modules whose restrictions to the universal enveloping algebra of the abelian nilradical of a maximal parabolic subalgebra are free of rank $1$. We show that they generically are simple, and give an explicit description of submodules in the non-simple case. This category embodies a certain connection between weight modules and non-weight modules.

math.RT↗

arXiv2026

DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation

Reasoning segmentation aims to predict pixel-wise masks for targets given complex language queries. Existing approaches leverage Multimodal Large Language Models (MLLMs) for vision-language reasoning and generate intermediate target cues (e.g., points or boxes) to guide a segmentation model. However, compressing rich reasoning into sparse cues often introduces ambiguity and noise, preventing these cues from accurately preserving the reasoning intent. While multiple complementary cues can enrich target information, existing methods typically feed them jointly into a single segmentation process, allowing ambiguous or erroneous cues to affect the entire prediction. Therefore, we propose DGSeg, a reasoning segmentation framework that learns to fuse predictions guided by semantic and spatial cues. Specifically, the MLLM jointly reasons about both target identity and spatial location, producing complementary semantic and spatial cues that are fed into separate segmentation branches. Their predictions are adaptively integrated by a lightweight dynamic gating module trained with relative branch-quality supervision to suppress noisy or conflicting regions. Extensive experiments demonstrate that DGSeg consistently outperforms strong baselines on multiple benchmarks and achieves 69.6% and 67.3% gIoU on the challenging ReasonSeg validation and test splits. Code is available at https://github.com/RZZeng/DGSeg.

cs.CV↗

arXiv2026

CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models

Vision-Language-Action (VLA) models have become a promising paradigm for generalist robot manipulation, where visual-language representations are used to condition continuous action generation. However, these representations are not explicitly optimized for action conditioning, leaving the action expert to bridge the gap between multimodal understanding and precise motor control. Recent action-reasoning methods introduce additional modules to generate explicit action plans or action-space reasoning signals, demonstrating the benefit of action-level guidance but often requiring separate action-generation frameworks. We propose CAC-VLA, a Context-Gated Action Conditioning framework that learns a lightweight latent-action interface directly within the VLM. Instead of generating executable trajectories, CAC-VLA trains the VLM to predict coarse-to-fine latent actions, which are structured representations encoded from future action segments, and adaptively leverages them to condition the action expert via a context gate. This enables VLM-native action conditioning while calibrating the influence of latent-action guidance on expert action generation. Experiments on LIBERO and LIBERO-Plus demonstrate the effectiveness of CAC-VLA, achieving 98.3% average success rate on LIBERO and 89.5% LIBERO-Plus, suggesting that context-gated latent-action conditioning is an effective interface for continuous expert control.

cs.RO↗

arXiv2026

Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction?

Predicting biomolecular properties from limited labeled data is a central bottleneck in protein engineering and small-molecule design. As strong pretrained encoders now supply rich fixed-length representations, the difficulty has shifted from representation learning to building a data-efficient predictor for the few-shot regime. Tabular foundation models such as TabPFN and TabICL are unlikely candidates for this role: they are in-context learners pretrained on synthetic tables drawn from random causal graphs, a generative prior with no obvious correspondence to the processes that produce protein sequences or molecular graphs. That this tabular, causal inductive bias should transfer to biomolecular data at all is counter-intuitive, yet we find it does. Treating each method as a predictor-representation pair, we evaluate across two domains. We find that on protein fitness regression tasks these in-context learning models coupled with ESM Cambrian representations achieve or exceed state-of-the-art results on ProteinGym, and outperform task-specific supervised regressors on a diverse esterase catalytic activity dataset. For small-molecule classification with ECFP/RDKit descriptors, no single predictor-representation pairing dominates across TDC ADMET, MoleculeNet, FS-Mol, and DrugOOD, but they are competitive with the existing task-specific state-of-the-art. Crucially, on both protein and small-molecule few-shot tasks, these predictor-representation pairs offer strong performance. We conclude that tabular foundation models can be strong biomolecular predictors, but only when coupled with expressive representations.

cs.LG↗

arXiv2026

FeatX: Editing Software by Editing Features for Repository-Level Code Evolution

Large language models (LLMs) are increasingly used for software evolution, yet most interaction paradigms remain code-centric and require manual context management and prompt iteration. We present FeatX, a feature-oriented tool for editing software by editing features. Given an existing repository, FeatX extracts a hierarchical epic-feature structure with explicit feature-to-code mappings, then invokes a three-stage Evolution Agent to translate feature edits into code patches. The workflow is exposed through four coordinated panels. Across a controlled user study and replay experiments on 38 real-world feature-editing commits, FeatX significantly reduces cognitive load and improves usability compared with vanilla ChatGPT. It also achieves a 42.6\% relative improvement in function-level modification localization F1 over strong LLM baselines, at substantially lower cost (\$0.07 in total). The tool and collected dataset are available at https://github.com/a496263365/FeatX/tree/demo, with a demonstration video at https://youtu.be/OZqKZ4Ii-yM.

cs.SE↗

arXiv2026

Low Complexity Kolmogorov-Arnold Network-based DPD for Analog RoF Fronthaul

This paper proposes and demonstrates experimentally for the first time a Kolmogorov-Arnold Network (KAN)-based digital predistortion (DPD) model, named envelope time-delay KAN (ETDKAN), for mitigating nonlinear distortions in analog radio-over-fiber (A-RoF) systems. The ETDKAN model incorporates physical constraints of radio-frequency (RF) nonlinear devices and, through KAN symbolization, achieves a significant reduction in computational complexity while improving interpretability. The proposed model is numerically implemented and optimized alongside multilayer perceptron (MLP) and memory-polynomial-based DPDs. Results show that the resulting symbolic ETDKAN (symbETDKAN) attains ACLR and EVM performance comparable to neural network-based models, while maintaining a computational complexity close to that of memory polynomials. Experimental validation using an A-RoF system confirms the practical feasibility of the proposed approach, which resulted in a 4-5 dB reduction in ACLR in the analyzed scenario.

eess.SP↗

arXiv2026

Probing Anomalous $t{\bar q}Z$ Interactions at Muon Colliders

In the framework of effective field theory, we study the anomalous $t{\bar q}Z$ interaction through the process $\mu^+\mu^- \to t{\bar q}Z$ at future muon colliders with $\sqrt s= 3, 10, 14\,\text{TeV}$. Based on the top quark decay modes involving $W$ and $Z$ bosons, we first divide the signal into six cases. Then, in order to obtain the limits on the corresponding branching ratios, we perform a detector simulation for both signals and Standard Model backgrounds. To enhance the signal significance, we exploit the polarization of the muon beams and employ the fat jet method to reconstruct signals in hadronic final states. For $\sqrt s= 14\,\text{TeV}$ with $20\,\text{ab}^{-1}$, we find that the upper limit on the branching ratio for $t\to qZ$ can reach the order of $\mathcal{O}(10^{-8})$, which exceeds the limits provided by the CMS and ATLAS collaborations by 2 to 3 orders of magnitude. Our study thus demonstrates that TeV-scale muon colliders can provide an efficient and complementary platform for probing rare top quark interactions.

hep-ph↗

arXiv2026

Integrated Terahertz Photonic Receiving Frontend with Link Noise Outperforming Electronics

Terahertz technology is a key enabler for sixth-generation (6G) wireless networks, yet its application is constrained by increasingly severe free-space loss at high frequencies. To efficiently retrieve weak signals at the receiving end, a compact frontend that features both a high-gain antenna and a low-noise signal-detection chain is critical. Current transistor-based THz electronic frontends face significant challenges in meeting these demands because both on-chip antenna efficiency and transistor noise performance degrade rapidly when approaching their cut-off frequencies. Photonic technology provides an alternative solution to circumvent the transistor bandwidth limit, yet most microwave photonic links to date exhibit noise performance substantially worse than state-of-the-art electronics. Here, we demonstrate low-noise integrated THz photonic frontends that deliver undegraded link noise performance across three major THz windows from 140 to 450 GHz, and outperform electronic frontends in the upper two windows. We achieve this through co-design of high-gain on-chip THz antenna array and broadband THz-optic modulator on a single thin-film lithium niobate (TFLN) chip, leading to distributed reception of free-space THz signals and continuous coherent build-up of the THz-optic conversion process with unprecedented efficiency. Combined with an efficient heterodyne detection chain, our integrated frontends exhibit effective isotropic noise figures of 13.6 and 16.2 dB at 250 and 450 GHz, respectively, both setting new benchmarks in their respective bands. We further demonstrate 6G-oriented multi-link communication up to 20 Git/s. Our integrated frontends represent a significant step towards compact, cost-effective and energy-efficient THz wireless systems in 6G and beyond.

physics.optics↗