arXiv subjects

Wei Liu

Publications and source records attributed to Wei Liu.

At least 91 records · Page 5Linked to original sources

arXiv2026

GUI-PRA: Process Reward Agent for GUI Tasks

Long-horizon GUI automation remains challenging due to error accumulation over extended interaction sequences. Process Reward Models (PRMs) provide dense step-level supervision for mitigating error accumulation, yet standard PRMs are poorly suited to GUI verification. Standard PRM judgments often rely on superficial visual alignment rather than functional correctness, reflecting an evaluative knowledge gap caused by missing domain-specific adjudication logic. Standard PRMs also perform passive, single-pass visual assessment, which creates Visual Ambiguity when reliable judgment requires actively locating, parsing, or inspecting task-relevant UI evidence. We introduce GUI-PRA, a Process Reward Agent that transforms GUI process evaluation from passive scoring into active investigation. GUI-PRA couples Experience-Injected Criterion Synthesis, which distills generalized verification principles into state-specific criteria, with Criterion-Guided Autoregressive Perception, which uses these criteria to navigate multi-granularity visual tools and gather grounded evidence. On AndroidWorld and Mobile-MiniWoB++, GUI-PRA achieves improvements of 5.0% and 6.5% over standard PRMs on the Qwen-VL series, with Qwen3-VL attaining 54.74% success rate on AndroidWorld. On the offline OS-Critic Bench, GUI-PRA demonstrates strong competitiveness against fully trained critic models.

cs.AI↗

arXiv2026

Decoupled Structure-Feature Alignment via Alternating Optimization for Graph Learning

Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which often renders them vulnerable to topological noise and heterophilous connections. To decouple this dependency, we present a constrained two-view learning framework for robust graph learning, which aligns structure-aware GNN embeddings with a structure-free feature prior. Specifically, the proposed Decoupled Structure-Feature Alternating Learning (DSAL) framework trains an independent anchor network using a self-supervised reconstruction objective to capture the intrinsic semantic information contained in node attributes. Within DSAL, to effectively integrate this prior, we design a channel-split adaptive gated (CSAG) layer. This architecture employs a gating mechanism to balance global spectral smoothing and local spatial representation dynamically. Furthermore, the model is optimized via a cyclic alternating procedure, which mitigates representation drift caused by mutual interference in standard joint optimization schemes. Experiments on diverse homophilous and heterophilous datasets suggest that our proposed approach provides improved node classification accuracy while maintaining robustness to structural perturbations compared to standard message-passing architectures.

cs.LG↗

arXiv2026

Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding

The integration of novel view synthesis (NVS) and open-vocabulary segmentation (OVS) has recently yielded powerful feed-forward 3D foundation models. However, their inherent reliance on static-scene assumptions leads to severe misalignment of spatial features in unconstrained dynamic environments. To bridge this critical gap, we propose SPAR, a novel joint semantic-geometric encoding architecture that explicitly isolates transient dynamic noise prior to latent space aggregation. Furthermore, we introduce a dynamic-region-aware end-to-end training paradigm that structurally couples motion estimation with multi-view visual and semantic learning. This unified approach enables the network to inherently resolve motion conflicts and distill multi-view consistent, temporally stable scene representations from dynamic inputs. Extensive experiments on the challenging D-RE10K benchmark demonstrate that SPAR achieves state-of-the-art performance. Our end-to-end approach achieves exceptional novel view synthesis quality, yielding a PSNR of 22.15 dB and 23.33 dB given only 3 and 4 input views respectively. Despite being trained in a self-supervised manner, our model achieves an mIoU of 88.5% for motion mask prediction. Furthermore, our analysis reveals a strong inter-task synergy between photometric scene reconstruction and semantic understanding, where semantic synthesis learning consistently enhances photometric fidelity in novel view rendering. Code will be available at https://github.com/dmucby/SPAR.

cs.CV↗

arXiv2026

Mixture of Multicenter Experts in Multimodal AI for Debiased Radiotherapy Target Delineation

Clinical decision-making reflects diverse strategies shaped by regional patient populations and institutional protocols. However, most existing medical artificial intelligence (AI) models are trained on highly prevalent data patterns, which reinforces biases and fails to capture the breadth of clinical expertise. Inspired by the recent advances in Mixture of Experts (MoE), we propose a Mixture of Multicenter Experts (MoME) framework to address AI bias in the medical domain without requiring data sharing across institutions. MoME integrates specialized expertise from diverse clinical strategies to enhance model generalizability and adaptability across medical centers. We validate this framework using a multimodal target volume delineation model for prostate cancer radiotherapy. With few-shot training that combines imaging and clinical notes from each center, the model outperformed baselines, particularly in settings with high inter-center variability or limited data availability. Furthermore, MoME enables model customization to local clinical preferences without cross-institutional data exchange, making it especially suitable for resource-constrained settings while promoting broadly generalizable medical AI.

eess.IV↗

arXiv2026

When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning

Language descriptions in source-free cross-domain few-shot learning (SF-CDFSL) are often selected according to zero-shot accuracy obtained with a frozen vision--language model. This paper asks whether that ranking remains valid after target-domain visual adaptation. Under a strictly paired protocol, we compare a generic class-name template with fixed detailed class descriptions before and after visual Low-Rank Adaptation (LoRA) on EuroSAT, CropDisease, ISIC, and ChestX. Let $\deltazero$ and $\deltalora$ denote the Detailed-minus-Base accuracy before and after adaptation, respectively. Two recurring regimes emerge. In \emph{semantic saturation}, $\deltazero>0$ but $0<\deltalora\ll\deltazero$: on EuroSAT and CropDisease, initial gains of 8.13--21.54 percentage points contract to 0.69--2.96 points after LoRA. In \emph{semantic emergence}, $\deltazero\leq0$ but $\deltalora>0$: on ISIC and ChestX, detailed descriptions become more useful only after the visual representation is updated. Training trajectories and sample-level decomposition show that saturation is driven mainly by Base-LoRA recovering errors already solved by detailed semantics, whereas emergence is associated with prediction turnover and newly formed Detailed-only correct decisions. Fixed-point-free shuffled-semantic controls, a second CLIP backbone, and multiple random seeds support the broad pattern while identifying ChestX 1-shot as a weak boundary case. These findings establish that zero-shot prompt quality is an incomplete proxy for adaptation-anchor quality and motivate evaluating language on both sides of the adaptation boundary.

cs.CV↗

arXiv2026

A Unified Descriptive-Complexity Framework for Model Selection under Correlated Designs

Model selection becomes particularly challenging under strong predictor dependence and model-class uncertainty, especially when there are exponentially many models. We propose a Descriptive-Complexity Information Criterion (DCIC) that regularizes large candidate model collections through Kraft-admissible code lengths. Under sub-Weibull noise, we establish selection consistency through approximation-error separation without relying on RIP-type conditions, together with nonasymptotic oracle risk bounds that remain valid under model misspecification. The same coding principle places heterogeneous classes on a common complexity scale at a small additional class-identification cost. This extension yields class--model recovery under suitable identifiability conditions and risk adaptation across classes. We further develop a complexity-guided search path that makes the computation--statistics trade-off explicit. Large penalties yield polynomial-size retained search regions with high probability, whereas smaller penalties sharpen the oracle risk benchmark. Numerical experiments illustrate stable support recovery and favorable estimation performance under strong dependence and model-class uncertainty.

stat.ML↗

arXiv2026

Scaling Muon for Diffusion Transformers

The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion Transformers (DiTs) remain unclear. We first establish Muon's scaling behavior on DiTs from 1.3B to 15B parameters, showing that its optimization and generative quality advantages over AdamW persist across model scales. However, at scale, the 5-step Newton--Schulz iteration (NS5) performed at every optimization step, together with full-momentum materialization, introduces substantial computation and communication overhead that can offset Muon's step-efficiency advantage. We introduce \emph{Periodic Row-wise Muon}, which performs a full NS5 spectral update once every $K$ steps and applies a low compute and communication cost row-wise constrained update based on the current momentum at the remaining steps. We further co-design a distributed implementation that operates directly on sharded momentum during non-refresh steps and accelerates spectral refreshes through bucketed all-gather and communication--computation overlap. Across all scales, Muon improves the best observed generative quality over AdamW by 12.9--19.1\%. Compared with vanilla Muon, Periodic Row-wise Muon remains within 0.5\% in best generative quality on the 1.3B--4B models and improves it by 4.5\% at 9B. It reduces optimizer time by 46.9--54.3\%, end-to-end step time by 15.7--24.3\%, and logical communication volume by 66.7\%, while reaching its respective best generative quality with 33.7--64.8\% less active training time. These results show that Periodic Row-wise Muon preserves Muon's generative quality advantage while translating it into end-to-end training efficiency for large DiTs.

cs.LG↗

arXiv2026

Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios

Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding. However, their ability to follow instructions in this domain remains under-explored. Real-world video understanding requires models not only to interpret video content correctly, but also to satisfy diverse user-specified constraints. Existing benchmarks focus primarily on task accuracy rather than instruction adherence, leaving this capability insufficiently evaluated. To address this gap, we introduce Video-IFBench, a comprehensive benchmark for evaluating instruction following in video understanding, where models must satisfy diverse user-specified constraints, including those grounded in visual and audio content. We develop an instruction taxonomy with four templates, including single-task, multi-task, selection, and nested instructions, covering 32 task types and 39 manually designed constraint categories spanning both semantic and format requirements. To reduce annotation cost, we build a semi-automatic data construction pipeline that combines MLLMs, programmatic processing, and human verification, resulting in 1.5K samples. We conduct a large-scale evaluation of more than 20 recent MLLMs and show that video instruction following remains challenging for current models, especially for instructions with many constraints, semantic constraints, or complex conditional structures that require selecting the correct branch or path based on video content. We hope our work will facilitate future research on instruction following in video understanding scenarios.

cs.CV↗

arXiv2026

Molecular LLM Agents: From Architectural Design to Scientific Autonomy

Molecular science represents an important frontier for LLM-based agents. Unlike general agents that mainly operate over natural language, code, or web environments, molecular LLM agents must perceive, reason about, and act upon chemical objects across symbolic strings, molecular graphs, 3D conformations, spectra, simulations, and wet-lab measurements. Their capabilities depend on chemically faithful molecular perception, an LLM-centered agent framework, domain-specific tool grounding, and computational or experimental feedback, in addition to planning and tool use. This work develops a conceptual framework for molecular LLM agents from two complementary perspectives. First, we introduce an architectural view of molecular-agent design, covering molecular representation and perception, the agent framework, domain-specific toolboxes, and learning and optimization. Second, we propose a scientific autonomy ladder inspired by staged autonomy in engineering systems, categorizing agents into four levels: L1 assistive or fixed workflows, L2 adaptive computational agents, L3 feedback-aware physical experiment agents, and L4 scientific-agenda agents. Together, these two perspectives establish a comprehensive framework for comparing existing molecular LLM agents, identifying missing capabilities and deployment risks, and guiding the design, evaluation, and deployment of future agents in molecular discovery workflows.

cs.CL↗

arXiv2026

Task-Adaptive Rubrics for GUI Reward Modeling

Recent studies on GUI agents have increasingly focused on outcome reward modeling, which assigns outcome rewards by judging whether an executed trajectory satisfies the success criteria implied by the user instruction. Existing GUI reward verifiers, however, often under-specify how these criteria should be constructed for each task instance. Whether using generic rubric structures or implicit model reasoning, their judging criteria are not sufficiently task-adaptive: they can transfer checks across tasks, overlook concrete constraints in the current instruction, or become overly strict by enforcing unstated requirements. To address this limitation, we propose AdaptRubric, a Coarse-to-Fine Rubrics Framework that constructs task-adaptive judging criteria through a category-level coarse stage and an instance-level fine stage. AdaptRubric performs category-level coarse rubric retrieval by routing the instruction to a GUI task family and retrieving reusable task-family criteria, then conducts instance-level fine rubric generation to surface compact cues for concrete values, scopes, and constraints in the current instruction. Across offline reward evaluation and online reinforcement learning optimization, AdaptRubric consistently outperforms prior reward agents, improving F1 by 3.6 points over the baseline average under a matched image budget and yielding a 4.23-point task-success gain.

cs.AI↗

arXiv2026

On-Policy Self-Distillation in Diffusion Models

Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries. At each outer iteration, a frozen behavior policy generates trajectories and supplies query states and anchors. Reward gradients construct bounded positive and negative targets around each anchor. The trainable policy fits these targets as detached supervision through finite fitting before an exponential moving average update refreshes the behavior policy. This setup lets us measure target construction and finite realization separately. Controlled same-query experiments show that larger target-construction gains do not necessarily translate into larger realized gains after a single fitting update. Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators. It outperforms the strongest competing method by up to 44.0% and reduces training GPU-hours relative to DiffusionNFT by 40% on SD 3.5-M and 63% on Z-Image-Turbo. These results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.

cs.CV↗

arXiv2026

Long-Integration Magnetar Burst Observatory (LIMBO): Instrument Summary and Early FRB Rate Constraints

The Long-Integration Magnetar Burst Observatory (LIMBO) is a real-time radio transient detection pipeline designed to search for dispersed fast radio bursts (FRBs) from Galactic magnetars. Deployed at the University of California, Berkeley's Leuschner Radio Observatory, LIMBO employs a $4.3~\mathrm{m}$ dish with a dual-polarization feed to continuously monitor a $125~\mathrm{MHz}$ band centred at $1460~\mathrm{MHz}$. A real-time processing pipeline performs a search for dispersed transients on the summed polarizations, with detections triggering dumps of buffered voltage data to disk. Based on calibrated sensitivity measurements, synthetic signal-injection and recovery tests, and successful detection of pulses from the Crab Pulsar, we determine that LIMBO is sensitive to radio transients with fluences $\geq 43~\mathrm{Jy \cdot ms}$. Between May and August 2023, LIMBO conducted 833 hours of follow-up observations of the Galactic magnetar SGR 1935+2154, yielding 12 candidate FRB detections. If these events are true, we measure FRB-like event rates from SGR 1935+2154 of $R(\geq 65~\mathrm{Jy \cdot ms}) = 112.3^{+81.3}_{-54.5}~\mathrm{yr}^{-1}$ and $R(\geq 130~\mathrm{Jy \cdot ms}) = 17.7^{+40.8}_{-15.1}~\mathrm{yr}^{-1}$. Combining these results with previously reported FRBs from SGR 1935+2154, we infer a cumulative rate-fluence power-law slope of $α=-0.60^{+0.24}_{-0.28}$ in the fluence range between $10$ and $10^6\rm\, Jy \cdot ms$. These observations demonstrate the capability of continuous, real-time monitoring of Galactic magnetars and establish LIMBO as an effective instrument for detecting Galactic FRBs.

astro-ph.IM↗

arXiv2026

GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis

Vision-Language Models (VLMs) based GUI agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental issues: current data synthesis methods for GUI Agents rely on specific environments and struggle to generate diverse data, while existing evaluators either suffer from limited scalability or provide inaccurate and unreliable reward signals. To overcome these challenges, we introduce GSAR (Goal-State-Anchor Reward), a RL reward framework that supports scalable task generation and delivers reliable reward signals for stable and efficient policy optimization. Our approach features self-evolving data synthesis, which produces multiple environments through task execution and generates diverse tasks and goal states. Complementing this, a state-anchor mechanism automatically annotates task-relevant UI elements in successful goal states as reference anchors. During RL training, these reference anchors provide accurate, scalable reward signals that substantially enhance efficiency. Extensive evaluations demonstrate that our framework achieves over 90% accuracy on offline trajectory verification and performs closest to rule-based methods. Furthermore, agents trained using our reward framework exhibit strong performance on both AndroidWorld and our constructed benchmark, establishing a scalable approach for GUI agent training.

cs.AI↗

arXiv2026

GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI

In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual contexts or evaluating execution-time dynamics, but the complementary axis of fixing the scene and varying only the instruction remains underexplored. We introduce GuardianBench, an instruction-contrastive benchmark grounded in international safety standards that isolates this latent contextual risk through 3,024 instruction-scene examples organized as same-scene Safe/Unsafe contrastive pairs across various hazard categories. Benchmarking state-of-the-art vision-language models (VLMs) reveals instruction-insensitive verdicts: models disproportionately approve both instructions under a given scene; across the primary models, average pair accuracy is only 24.1%. Our systematic rationale audit localizes the dominant failure: models fail to bind the instruction-relevant cues that differentiate safe from unsafe compositions. As a post-training case study, Verdict Log-Odds Supervision (VLOS), a lightweight verdict-level objective, substantially improves performance on open-weight backbones. Together, our latent contextual risk task formulation, standards-grounded contrastive benchmark construction, pair-level and rationale-level failure diagnosis, and benchmark-enabled verdict calibration establish GuardianBench as a controlled evaluation suite for exposing and improving safety reasoning over instruction-scene compositions under latent contextual risk.

cs.AI↗

arXiv2026

Artificial Anisotropy Induced Bound States in the Continuum for Integrated Photonic Waveguide

Bound states in the continuum (BICs) enable counterintuitive light confinement without radiation loss, providing a powerful foundation for integrated photonic waveguides. However, existing BIC waveguides are predominantly realized through geometry-dependent designs, where the BIC condition is restricted to narrowly defined structural parameters, limiting design flexibility and practical applicability. Artificial optical anisotropy is introduced as a new design paradigm for BIC waveguides. Implemented using subwavelength-grating (SWG) metamaterials, continuously tailorable anisotropy provides an independent degree of freedom for deterministically reshaping the radiative continuum, enabling flexible formation and systematic control of BIC waveguides over a broad design space. Anisotropy-engineered symmetry breaking further enables controllable asymmetric radiation and precisely tailored field leakage. This paradigm transforms BIC waveguides from geometry-constrained structures into an anisotropy-engineered platform, establishing a general framework for programmable radiation engineering and next-generation integrated photonic devices.

physics.optics↗

arXiv2026

Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation

Generative Recommendation (GR) has emerged as a new paradigm for sequential recommendation, in which a representative line of work encodes items into hierarchical semantic IDs via residual quantization and predicts the IDs token by token. However, this generative formulation still exhibits structural gaps with respect to the recommendation task: flattening multi-token IDs into a single sequence destroys item-level structure, and the inconsistency between training and inference over a hierarchical codebook gives rise to semantic drift. To bridge these two gaps, we propose BARGE, which employs Item Context-Aware Attention (ICA) to restore item-level structure during encoding, and Hierarchical Path Reranking (HPR) together with Dual-Path Decoding (DPD) to suppress semantic drift from two complementary angles during decoding. Extensive experiments and analytical studies on public benchmarks and a large-scale offline test demonstrate that BARGE achieves superior recommendation performance. An online A/B test on a Tencent platform yields improvements of 0.60% in click-through rate, 1.34% in click unique visitors, and 1.70% in total reading time, confirming the practical value of BARGE in industrial-scale recommendation.

cs.IR↗

arXiv2026

G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution

Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on linear sequential reasoning for both trajectory generation and inference, making it difficult to consistently preserve intermediate states and constraints throughout long-horizon multi-hop search. Consequently, they often suffer from context forgetting, search drift, and inefficient exploration. To address these limitations, we propose $\textbf{G-ReAct}$, a reasoning framework for deep search that organizes reasoning as $\textbf{state evolution over a fixed-topology query graph}$. The evolving graph state explicitly tracks search progress and guides subsequent decisions, transforming exploratory search driven by textual history into graph-guided reasoning under explicit constraints. G-ReAct supports both training and inference: it generates high-quality deep-search trajectories for supervised fine-tuning and provides structured guidance for inference-time search without additional fine-tuning. Experiments demonstrate that with only 1.9K generated trajectories for fine-tuning, Qwen3-30B-A3B-Thinking-2507 achieves $52.6\%$ accuracy on BrowseComp-ZH and $79.0\%$ on XBench, outperforming comparable open-source methods trained on substantially larger datasets, including RL-enhanced methods. Furthermore, when applied at inference time, G-ReAct consistently improves the performance of existing strong LLMs on deep-search tasks. We will publicly release all code and model weights.

cs.AI↗

arXiv2026

SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis

Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-coverage, long-horizon interaction trajectories collected from element-rich and rapidly evolving apps. Existing pipelines often rely on costly human demonstrations or on-policy framework, which tends to over-sample common flows while missing rare transitions and complex multi-step procedures. To address this problem, we propose SEE, a two-stage data synthesis framework consisting of (i) an efficient exploration stage that builds an explicit UI transition graph over screens and elements, and (ii) a graph-based synthesis stage that composes diverse multi-step trajectories via planning and controlled sampling. This design yields reproducible and explainable data generation, while explicitly preventing spurious cycles and enabling long-horizon composition. Across multiple real-world apps, SEE produces trajectories with an average length of 14.8 steps while avoiding spurious loops, and agents fine-tuned on SEE achieve improved task success and generalization to unseen screens. We will publicly release our synthesis code and dataset.

cs.LG↗