arXiv subjects

Wei Jiang

Publications and source records attributed to Wei Jiang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training

Vision-language model-based mobile agents have gained the ability to understand complex instructions and mobile screenshots, benefiting from reinforcement learning paradigms like Group Relative Policy Optimization (GRPO). However, existing approaches centers on offline training or local action-level rewards often trap agents in local optima, hindering effective exploration and error correction with the environment. Crucially, we find that directly applying task-level rewards often leads to convergence difficulties due to the sparse nature of GUI interactions. To address these challenges, we present \textbf{Mobile-R1}, a systematic training recipe that bridges atomic action execution and strategic task completion. We propose a hierarchical curriculum consisting of three stages: (1) format alignment for reasoning structure, (2) on-policy exploration with verifiable action feedback to ground basic execution, and (3) multi-turn task-level training with realistic environment to unlock exploration and self-correction. This hierarchical strategy effectively bootstraps the agent, significantly enhancing its capability for exploration and self-correction (the ``Eureka'' moments). Furthermore, addressing the critical scarcity of diverse GUI data in non-English ecosystems, we contribute a comprehensive Chinese mobile dataset covering 28 applications with 24,521 high-quality manual annotations, and establish a rigorous benchmark with 500 trajectories. We will open source all resources, including the dataset, benchmark, model weight, and codes: https://mobile-r1.github.io/Mobile-R1/.

cs.AI↗

arXiv2026

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning

Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. However, the current fully autonomous paradigm poses potential safety risks when model understanding or reasoning capabilities are insufficient. To address this challenge, we first introduce \textbf{InquireBench}, a comprehensive benchmark specifically designed to evaluate mobile agents' capabilities in safe interaction and proactive inquiry with users, encompassing 5 categories and 22 sub-categories, where most existing VLM-based agents demonstrate near-zero performance. In this paper, we aim to develop an interactive system that actively seeks human confirmation at critical decision points. To achieve this, we propose \textbf{InquireMobile}, a novel model inspired by reinforcement learning, featuring a two-stage training strategy and an interactive pre-action reasoning mechanism. Finally, our model achieves an 46.8% improvement in inquiry success rate and the best overall success rate among existing baselines on InquireBench. We will open-source all datasets, models, and evaluation codes to facilitate development in both academia and industry.

cs.AI↗

arXiv2026

Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) enables cross-modality identity matching for all-day surveillance, yet existing methods predominantly focus on the image level or rely heavily on costly identity annotations. While video-based VI-ReID has recently emerged to exploit temporal dynamics for improved robustness, existing studies remain limited to supervised settings. Crucially, the unsupervised video VI-ReID problem, where models must learn from RGB and infrared tracklets without identity labels, remains largely unexplored despite its practical importance in real-world deployment. To bridge this gap, we propose HiTPro (Hierarchical Temporal Prototyping), a prototype-driven framework without explicit hard pseudo-label assignment for unsupervised video-based VI-ReID. HiTPro begins with an efficient Temporal-aware Feature Encoder that first extracts discriminative frame-level features and then aggregates them into a robust tracklet-level representation. Building upon these features, HiTPro first constructs reliable intra-camera prototypes via Intra-Camera Tracklet Prototyping by aggregating features from temporally partitioned sub-tracklets. Through Hierarchical Cross-Prototype Alignment, we perform a two-stage positive mining process: progressing from within-modality associations to cross-modality matching, enhanced by Dynamic Threshold Strategy and Soft Weight Assignment. Finally, {Hierarchical Contrastive Learning} progressively optimizes feature-prototype alignment across three levels: intra-camera discrimination, cross-camera same-modality consistency, and cross-modality invariance. Extensive experiments on HITSZ-VCM and BUPTCampus demonstrate that HiTPro achieves state-of-the-art performance under fully unsupervised settings, significantly outperforming adapted baselines and establishes a strong baseline for future research.

cs.CV↗

arXiv2026

Atomic-scale visualization of d-wave altermagnetism

Altermagnetism is a newly identified magnetic phase, distinct from conventional ferromagnetism and antiferromagnetism. It exhibits no net magnetization while breaking time-reversal symmetry. Although its momentum-space signatures are established, direct real-space visualization of its defining rotational-symmetry breaking remains missing. Here, using scanning tunnelling microscopy, we provide atomic-scale real-space evidence for altermagnetism in CsV2Se2O. Utilizing intrinsic spin defects as probes, we directly visualize the hallmark symmetry breaking through unidirectional electronic patterns and elliptical charging rings, both tied to the alternating spin texture. Moreover, adjacent spin-defect lines exhibit opposite spins and long-range antiferromagnetic coupling, hinting at a novel spin order. Our work moves the field from momentum-space probes to direct real-space visualization, opening a path to explore how this unconventional magnetic order couples to other quantum states.

cond-mat.mtrl-sci↗

arXiv2026

Seeing Beyond RGB Capabilities: Data-Driven and Physics-Guided Broadband Spectral Extrapolation of Plasmonic Nanostructures by Deep Learning

Localized surface plasmons can confine light within a deep-subwavelength volume comparable to the scale of atoms and molecules, enabling ultrasensitive responses to near-field variations. On the other hand, this extreme localization also inevitably amplifies the unwanted noise from the response of local morphological imperfections, leading to complex spectral variations and reduced consistency across the plasmonic nanostructures. Seeking uniform optical responses has therefore long been a sought-after goal in nanoplasmonics. However, conventional probing techniques by dark-field (DF) confocal microscopy, such as image analysis or spectral measurements, can be inaccurate and time-consuming, respectively. Here, we introduce SPARX, a deep-learning-powered paradigm that surpasses conventional imaging and spectroscopic capabilities. In particular, SPARX can batch-predict broadband DF spectra (e.g., 500-1000 nm) of numerous nanoparticles simultaneously from an information-limited RGB image (i.e., below 700 nm). It achieves this extrapolative inference beyond the camera's capture capabilities by learning the underlying physical relationships among multiple orders of optical resonances. The spectral predictions only take milliseconds, achieving a speedup of three to four orders of magnitude compared to traditional spectral acquisition, which may take from hours to days. As a proof-of-principle demonstration for screening identical resonances, the selection accuracy achieved by SPARX is comparable to that of conventional spectroscopy techniques. This breakthrough paves the way for consistent plasmonic applications and next-generation microscopies.

physics.optics↗

arXiv2026

From Pixels to Nucleotides: End-to-End Token-Based Video Compression for DNA Storage

DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low maintenance cost. Over the past decade, substantial progress has been made in storing text, images, and files in DNA -- yet video remains an open challenge. The difficulty is not merely technical: effective video DNA storage requires co-designing compression and molecular encoding from the ground up, a challenge that sits at the intersection of two fields that have largely evolved independently. In this work, we present HELIX, the first end-to-end neural network jointly optimizing video compression and DNA encoding -- prior approaches treat the two stages independently, leaving biochemical constraints and compression objectives fundamentally misaligned. Our key insight: token-based representations naturally align with DNA's quaternary alphabet -- discrete semantic units map directly to ATCG bases. We introduce TK-SCONE (Token-Kronecker Structured Constraint-Optimized Neural Encoding), which achieves 1.91 bits per nucleotide through Kronecker-structured mixing that breaks spatial correlations and FSM-based mapping that guarantees biochemical constraints. Unlike two-stage approaches, HELIX learns token distributions simultaneously optimized for visual quality, prediction under masking, and DNA synthesis efficiency. This work demonstrates for the first time that learned compression and molecular storage converge naturally at token representations -- suggesting a new paradigm where neural video codecs are designed for biological substrates from the ground up.

cs.CV↗

arXiv2026

Spike-PTSD: A Bio-Plausible Adversarial Example Attack on Spiking Neural Networks via PTSD-Inspired Spike Scaling

Spiking Neural Networks (SNNs) are energy-efficient and biologically plausible, ideal for embedded and security-critical systems, yet their adversarial robustness remains open. Existing adversarial attacks often overlook SNNs' bio-plausible dynamics. We propose Spike-PTSD, a biologically inspired adversarial attack framework modeled on abnormal neural firing in Post-Traumatic Stress Disorder (PTSD). It localizes decision-critical layers, selects neurons via hyper/hypoactivation signatures, and optimizes adversarial examples with dual objectives. Across six datasets, three encoding types, and four models, Spike-PTSD achieves over 99% success rates, systematically compromising SNN robustness. Code: https://github.com/bluefier/Spike-PTSD.

cs.CR↗

arXiv2026

NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories

Code editing is a frequent yet cognitively demanding task in software development. Existing AI-powered tools often disrupt developer flow by requiring explicit natural language instructions and suffer from high latency, limiting real-world usability. We present NES (Next Edit Suggestion), an instruction-free, low-latency code editing framework that leverages learned historical editing trajectories to implicitly capture developers' goals and coding habits. NES features a dual-model architecture: one model predicts the next edit location and the other generates the precise code change, both without any user instruction. Trained on our open-sourced SFT and DAPO datasets, NES achieves state-of-the-art performance (75.6% location accuracy, 27.7% exact match rate) while delivering suggestions in under 250ms. Deployed at Ant Group, NES serves over 20,000 developers through a seamless Tab-key interaction, achieving effective acceptance rates of 51.55% for location predictions and 43.44% for edits, demonstrating its practical impact in real-world development workflows.

cs.SE↗

arXiv2026

SecAgent: Efficient Mobile GUI Agent with Semantic Context

Mobile Graphical User Interface (GUI) agents powered by multimodal large language models have demonstrated promising capabilities in automating complex smartphone tasks. However, existing approaches face two critical limitations: the scarcity of high-quality multilingual datasets, particularly for non-English ecosystems, and inefficient history representation methods. To address these challenges, we present SecAgent, an efficient mobile GUI agent at 3B scale. We first construct a human-verified Chinese mobile GUI dataset with 18k grounding samples and 121k navigation steps across 44 applications, along with a Chinese navigation benchmark featuring multi-choice action annotations. Building upon this dataset, we propose a semantic context mechanism that distills history screenshots and actions into concise, natural language summaries, significantly reducing computational costs while preserving task-relevant information. Through supervised and reinforcement fine-tuning, SecAgent outperforms similar-scale baselines and achieves performance comparable to 7B-8B models on our and public navigation benchmarks. Our dataset is available at https://huggingface.co/datasets/alibabagroup/CMGUI.

cs.CV↗

arXiv2026

Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength. We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state. These impose contradictory data requirements: low-rated games provide the diversity needed for tracking, while high-rated games provide the quality signal for decision learning. Removing low-rated data degrades performance. We formalize this tension as a dual-capability bottleneck, P <= min(T,Q), where overall performance is limited by the weaker capability. Guided by this view, we scale the model from 28M to 120M parameters to improve tracking, then introduce Elo-weighted training to improve decisions while preserving diversity. A 2 x 2 factorial ablation shows that scaling improves tracking, weighting improves decisions, and their combination is superadditive. Linear weighting works best, while overly aggressive weighting harms tracking despite lower validation loss. We also introduce a coverage-decay formula, t* = log(N/kcrit)/log b, as a reliability horizon for intra-game degeneration risk. Our final 120M-parameter model, without search, reached Lichess bullet 2570 over 253 rated games. On human move prediction it achieves 55.2% Top-1 accuracy, exceeding Maia-2 rapid and Maia-2 blitz. Unlike position-based methods, sequence input naturally encodes full game history, enabling history-dependent decisions that single-position models cannot exhibit.

cs.AI↗

arXiv2026

Mapping the Midweek Mountain: The New Geography of Hybrid Work

This paper provides a behavioral analysis of the post-pandemic transformation of work, using a dataset of approximately 41 billion mobile geolocation records from 73.5 million individuals in the five largest U.S. metropolitan areas from the pre- to post- pandemic periods. By tracking movements between corporate headquarters, residences, and other points of interest, we document a structural shift in work patterns. Office based workdays declined from 42% in 2019 to 20.7% in 2022, before settling at 29.1% in 2023, a new equilibrium significantly below pre-pandemic levels. A "midweek mountain" peak of office attendance on Tuesdays through Thursdays, emerged as a robust new phenomenon post-pandemic. The nature of remote work has also changed: both in and after the pandemic, employees working from home allocated significantly more time to non-work locations like parks and malls during the workday. These findings indicate that the pandemic catalyzed a lasting transformation not just in work arrangements but also in the integration of personal and professional life, with implications for corporate policy, urban economics, and the future of work.

q-fin.CP↗

arXiv2026

LogPTR: Variable-Aware Log Parsing with Pointer Network

Due to the sheer size of software logs, developers rely on automated log analysis. Log parsing, which parses semi-structured logs into a structured format, is a prerequisite of automated log analysis. However, existing log parsers are unsatisfactory when applied in practice because they 1) ignore categories of variables, and 2) need labor-intensive model tuning. To address these limitations, we propose LogPTR, a variable-aware log parser that can extract the static and dynamic parts in logs, and further identify categories of variables. The key of LogPTR is formulating log parsing as a text summarization problem and using a pointer mechanism to copy words from the log message and label tokens indicating categories of variables. The experimental results on widely-used benchmark datasets show that LogPTR outperforms state-of-the-art log parsers on both general log parsing that extracts log templates and variable-aware log parsing that further identifies categories of variables.

cs.SE↗

arXiv2026

CRED: Counterfactual Reasoning and Environment Design for Active Preference Learning

As a robot's operational environment and tasks to perform within it grow in complexity, the explicit specification and balancing of optimization objectives to achieve a preferred behavior profile moves increasingly farther out of reach. These systems benefit strongly by being able to align their behavior to reflect human preferences and respond to corrections, but manually encoding this feedback is infeasible. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods sample from fixed trajectory sets or replay buffers that limit query diversity and often fail to identify informative comparisons. We propose CRED, a novel trajectory generation method for APL that improves reward inference by jointly optimizing environment design and trajectory selection to efficiently query and extract preferences from users. CRED "imagines" new scenarios through environment design and leverages counterfactual reasoning -- by sampling possible rewards from its current belief and asking "What if this were the true preference?" -- to generate trajectory pairs that expose differences between competing reward functions. Comprehensive experiments and a user study show that CRED significantly outperforms state-of-the-art methods in reward accuracy and sample efficiency and receives higher user ratings.

cs.RO↗

arXiv2026

Distributed vs. Centralized Precoding in Cell-Free Systems: Impact of Realistic Per-AP Power Limits

In cell-free massive MIMO, centralized precoding is {theoretically known} to {remarkably} outperform its distributed counterparts, albeit {with} high implementation complexity. However, this letter highlights a practical limitation {often overlooked:} {widely used closed-form} centralized {precoders} are typically derived under a sum-power constraint, which often demands unrealistic power allocation that exceeds hardware capabilities. {When two simple heuristics (global power scaling and local normalization) are applied to enforce the per-AP instantaneous power constraint}, the centralized performance superiority disappears, making distributed precoding {a robust option}.

cs.IT↗

arXiv2026

Adaptive Memory Admission Control for LLM Agents

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of conversational content, including hallucinated or obsolete facts, or depend on opaque, fully LLM-driven memory policies that are costly and difficult to audit. As a result, memory admission remains a poorly specified and weakly controlled component in agent architectures. To address this gap, we propose Adaptive Memory Admission Control (A-MAC), a framework that treats memory admission as a structured decision problem. A-MAC decomposes memory value into five complementary and interpretable factors: future utility, factual confidence, semantic novelty, temporal recency, and content type prior. The framework combines lightweight rule-based feature extraction with a single LLM-assisted utility assessment, and learns domain-adaptive admission policies through cross-validated optimization. This design enables transparent and efficient control over long-term memory. Experiments on the LoCoMo benchmark show that A-MAC achieves a superior precision-recall tradeoff, improving F1 to 0.583 while reducing latency by 31% compared to state-of-the-art LLM-native memory systems. Ablation results identify content type prior as the most influential factor for reliable memory admission. These findings demonstrate that explicit and interpretable admission control is a critical design principle for scalable and reliable memory in LLM-based agents.

cs.AI↗

arXiv2026

Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling

Vision-language models (VLMs) have been proven effective for detecting multi-modal misinformation on social platforms, especially in zero-shot settings with unavailable or delayed annotations. However, a single VLM's capacity falls short in the more complex mixed-source multi-modal misinformation detection (M3D) task. Taking captioned images as an example, in M3D, false information can originate from untruthful texts, forged images, or mismatches between the two modalities. Although recent agentic systems can handle zero-shot M3D by connecting modality-specific VLM agents, their effectiveness is still bottlenecked by their architecture. In existing agentic M3D solutions, for any input sample, each agent performs only one forward reasoning pass, making decisions prone to model randomness and reasoning errors in challenging cases. Moreover, the lack of exploration over alternative reasoning paths prevents modern VLMs from fully utilizing their reasoning capacity. In this work, we present AgentM3D, a multi-agent framework for zero-shot M3D. To amplify the reasoning capability of VLMs, we introduce an adaptive test-time scaling paradigm in which each modality-specific VLM agent applies a Best-of-N mechanism, coupled with a critic agent for task-aligned scoring. The agents are organized in a cascading, modality-specific decision chain to reduce unnecessary computation and limit error propagation. To ensure scalability, a planning agent dynamically determines the maximum number of reasoning paths based on sample difficulty, and an adaptive stopping mechanism prevents excessive reasoning within each agent. Extensive experiments on two M3D benchmarks demonstrate that AgentM3D achieves state-of-the-art zero-shot detection performance compared with various VLM-based and agentic baselines.

cs.MM↗

arXiv2026

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents

Recent advances in Vision-Language Models (VLMs) have motivated the development of multi-modal search agents that can actively invoke external search tools and integrate retrieved evidence through multi-step reasoning. While promising, existing approaches typically rely on large-scale supervised trajectories or expensive reinforcement learning (RL), leading to high training cost, instability, and a severe cold-start problem for standard VLMs. We propose a training-free paradigm to empower VLMs with autonomous search capabilities via cross-modal model merging. By fusing a text-based search agent with a base VLM, we show that multi-modal search capabilities can be effectively composed without any additional multi-modal training data. To mitigate parameter interference during cross-modal integration, we introduce Optimal Brain Merging (OBM), a saliency-aware merging algorithm that identifies task-critical parameters based on their impact on model loss using only a small set of calibration samples. Extensive experiments on search-intensive benchmarks (e.g., InfoSeek, MMSearch) reveal that: (1) Model merging secures a reasonable performance floor as a zero-shot agent, with OBM achieving superior search rates; (2) OBM significantly raises the performance ceiling as a warm-start strategy, achieving faster convergence and higher peak accuracy than standard VLM initialization.

cs.AI↗

arXiv2026

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentralized serving. This report presents xDeepServe, the production serving system behind Huawei Cloud's MaaS offering on CloudMatrix384, a 48-server SuperPod with 384 Ascend 910C chips connected by a high-bandwidth UB fabric and global shared memory. It serves models including DeepSeek, Kimi, GLM, Qwen, and MiniMax, among others. xDeepServe is built around Transformerless, a disaggregated execution architecture that decomposes transformer inference into modular units -- attention, feedforward, and MoE -- and supports disaggregated Prefill-Decode and MoE-Attention deployments. To enable disaggregation, we develop XCCL, a memory-semantic communication layer providing microsecond-level point-to-point and scalable all-to-all primitives, and we extend FlowServe with decentralized DP groups and techniques to mitigate stragglers and synchronization variance. In a peak decoding configuration, xDeepServe reaches 2400 tokens/s per Ascend 910C chip at ~50ms time-per-output-token (TPOT).

cs.DC↗