arXiv subjects

Wei Zhang

Publications and source records attributed to Wei Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Behind a Simple Read: Understanding Work and Waiting in the Linux I/O Stack

A simple read interface provides uniform semantics but unpredictable performance. Using synchronous large-buffer Linux reads, we decompose the buffered-read path into work volume, processing time, and critical-path exposure. Reducing local cost or accelerating request submission need not shorten a complete read. Linux uses large folios to reduce metadata work and I/O-copy overlap to hide most cold-read copying; an experimental kernel prototype shows that more aggressive overlap and parallelism can shorten the host path when these mechanisms fail. Device waiting dominates SSD cold reads. We abstract first-completion wait F and subsequent completion capacity B_CQ from request-batch timelines. Real-SSD experiments characterize their variation with request and batch size, while MQSim traces explain their internal origins. A wait chain along the folio-bio-request mapping connects device completion to upper-layer waiting. Under strict batching, the median absolute cross-layer prediction error is at most 7.43%. Finally, we apply the completion model and wait chain to request supply, Linux readahead, data layout, and waiting policies. Cases cover gains, no gains, and reversals, comparing predictions with interventions to close the loop from observation and modeling to understanding and control and provide a measurable basis for layered I/O decisions.

cs.OS↗

arXiv2026

ReInsVLN: Revisiting Historical Evidence for Training-Free Vision-and-Language Navigation

Vision-and-language navigation (VLN) relies on retaining and using relevant observations. Yet growing histories introduce redundancy, and retained information may remain underused. We introduce ReInsBench, a diagnostic benchmark that examines history utilization through controlled continuation trials. Its results show that history-review reinstruction can recover navigation failures using the existing task context. Motivated by this finding, we propose ReInsVLN, a training-free framework supporting memory construction and utilization in frozen navigators. Coverage- and Instruction-Aware Compression constructs compact visual context through temporal redundancy reduction, coverage-aware protection, and instruction-guided token selection. Forgetting-Inspired History Reminders guide navigators to revisit retained observations according to a predefined schedule, without additional model calls. On R2R Val-Unseen, ReInsVLN improves success rates by 8.48 and 3.37 percentage points over the native StreamVLN and InternVLA-N1, reaching 64.27% and 64.44%, respectively. Visual compression largely preserves navigation performance while reducing prefill latency and KV cache memory by up to 21.77% and 32.25%, respectively, on matched observation workloads. Real-world trials on humanoid and quadruped robots further support the applicability of ReInsVLN to sequential instruction following and ordinal navigation.

cs.RO↗

arXiv2026

Do in-silico metrics filter designed enzymes for catalysis?

Computational metrics are widely used to prioritize enzyme designs for experimental testing, yet their ability to capture catalytic function remains poorly established. Here, we systematically evaluate 33 in-silico metrics across four complementary tasks: distinguishing active from inactive enzymes, identifying substrate specificity, ranking enzyme variants by activity, and detecting perturbations to catalytic residues. We assess these capabilities using natural enzymes, computationally designed enzymes, activity-altering variants, and controlled structural perturbations that compare catalytic residues with matched non-catalytic sites. No single metric consistently captures all aspects of catalytic function. In activity discrimination, catalytic-residue intra-residue repulsion achieves the highest AUROC among the evaluated metrics for both natural enzymes (0.61) and 192 designs that passed the filters of their original design campaign (0.80). For substrate discrimination, interface predicted TM-score (ipTM) performs best (AUROC 0.70), whereas the catalytic pKa range shows the strongest association with activity across single-point variants of BglB (Spearman's rho = 0.48). In controlled perturbation tests, the minimum per-chain predicted TM-score (pTM) has a mean probability of 0.75 of responding more strongly to perturbations at catalytic residues than to matched perturbations at non-catalytic sites. These results reveal substantial variation in what current computational metrics capture, underscoring the need to distinguish structural confidence and physical plausibility from direct evidence of catalytic function when prioritizing enzyme designs.

cs.CE↗

arXiv2026

Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs

Visual token pruning for multimodal large language models (MLLMs) appears highly effective, with existing methods retaining over 95% of unpruned performance on common VQA benchmarks using a quarter of the visual tokens or fewer. However, our extensive evaluation of ten methods across three MLLM families and five ability groups reveals a critical gap: strong general performance often comes at the cost of severe degradation on fine-grained tasks such as OCR and visual grounding. We trace these failures to two limitations of the prevailing paradigm of retaining the highest-ranked native patches. A single importance ranking overlooks the complementary evidence required by different tasks, while sparse patch selection disrupts both image content and spatial integrity. To address these limitations, we propose Bifocal, a training-free, two-stage pruning method built on a mixed-granularity framework. It allocates separate budgets to query-focused and image-intrinsic evidence, complemented by a pooled coarse representation of the entire image. Before the LLM, Bifocal matches question words to visual regions through a soft conjunction balanced against norm-debiased image saliency, while selecting image-intrinsic evidence to maximize representational coverage. Inside the LLM, it further prunes tokens using density-adjusted text-to-image attention. With roughly a quarter of the original visual tokens, Bifocal is the only evaluated method to retain over 90% of unpruned performance in every ability group across all three models, and ranks first on average in all nine model-budget settings. The code is available at: https://github.com/EIT-NLP/Bifocal

cs.CV↗

arXiv2026

Perceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMs

Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most work uses LLMs as forecasters and classifiers, reasoning studies are few and narrow, and no suite trains and evaluates the full range of capabilities. In this paper, we build the first such suite, with 337K training and 44K evaluation samples across three progressive capabilities, Perceive, Solve, and Reason, and use it to ask how time series should enter an LLM that must master all three, and in what order. We find that a dedicated encoder is essential: with one, a 4B model surpasses GPT-4o on every perception attribute we test, whereas textualizing the series costs 8--10 points in reasoning accuracy. The capabilities then build on one another: learning them in order beats mixing the same data and rivals reasoning-only training with over three times the reasoning data, but only when an encoder is used. Analyses further reveal that capabilities are transferred through distinct network depths rather than simply stacked, and that a stage converged on its own benchmark is not necessarily ready for the next. Distilled into a simple recipe, these findings yield 4B TS-LLMs that, without any target-domain data, outperform four recent 7B TS-LLMs on seven of eight out-of-domain metrics, by up to 11 points. We therefore advocate treating time series as a first-class modality for LLMs, read through dedicated encoders and taught to perceive before they reason.

cs.CL↗

arXiv2026

Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation

LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A tampered deployment that preserves evaluated outputs passes every output-only evaluator. We introduce DIB-Bench, a benchmark that measures this deployment-integrity blindness across 7,560 scored examples, six tamper types, and an evaluator ladder from regex scorers through LLM judges to GPT-5-nano. Stronger evaluators accept more tampered outputs: mean acceptance rises from 88.6% (rule-based) to 94.1% (GPT-5-nano), and a trigger-conditional tamper invisible on the evaluation suite produces 48-100% harmful outputs, rising with model capability. A PAC-style bound shows that tampers with zero output shift are undetectable from outputs at any sample size; a manifest-hash identity channel detects them with zero samples. Behavioral fingerprinting identifies the model component above chance (76.7%) but covers one of six stack components. We also propose a graded deployment-identity descriptor for evaluation reports.

cs.CR↗

arXiv2026

BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport

Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits. BOLT (bound-oriented learning for transport-coupled scheduling) builds a lower bound from chain, machine-capacity, and fleet-capacity relaxations. The bound equals the makespan at termination, so its per-step changes form a reward that sums to a constant minus the makespan. Because it never exceeds the attainable makespan, each candidate's bound increase is a proven rise of the makespan floor, which the policy reads as a price. The root bound certifies a completed schedule's suboptimality gap without a solver. On industry-motivated 10-module prefabricated-construction instances, explicit transport coupling outperforms a transport-penalty policy in every tested cell where loaded moves occupy at least 66% of fleet time and in none at or below 56%. Across five zero-shot 50- and 80-module production batches, BOLT outperforms the best dispatching-rule pair on four and the penalty policy on the three with long moves. In the three-vehicle 80-module batch, its mean makespan is 13.0% below the best pair and 4.2% below an hour-budget constraint-programming solver whose proven gap averages 34%. BOLT decides in 2.3-5.9 ms per event on one processor core and re-plans a disruption in seconds.

cs.LG↗

arXiv2026

Penetration Testing for System Security: Methods and Practical Approaches

Penetration testing refers to the process of simulating hacker attacks to evaluate the security of information systems . This study aims not only to clarify the theoretical foundations of penetration testing but also to explain and demonstrate the complete testing process, including how network system administrators may simulate attacks using various penetration testing methods. Methodologically, the paper outlines the five basic stages of a typical penetration test: intelligence gathering, vulnerability scanning, vulnerability exploitation, privilege escalation, and post-exploitation activities. In each phase, specific tools and techniques are examined in detail, along with practical guidance on their use. To enhance the practical relevance of the study, the paper also presents a real-life case study, illustrating how a complete penetration test is conducted in a real-world environment. Through this case, readers can gain insights into the detailed procedures and applied techniques, thereby deepening their understanding of the practical value of penetration testing. Finally, the paper summarizes the importance and necessity of penetration testing in securing information systems and maintaining network integrity, and it explores future trends and development directions for the field. Overall, the findings of this paper offer valuable references for both researchers and practitioners, contributing meaningfully to the improvement of penetration testing practices and the advancement of cybersecurity as a whole.

cs.CR↗

arXiv2026

ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution

We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, and execution, yet reconciling generality with specialization across this spectrum remains an open challenge. Within a single unified model, ABot-ER commands specialist-level depth across all three competencies, spanning spatial, scene, and temporal reasoning in perception; long-horizon action organization in planning; and point grounding and affordance in execution. The Agentic Data-Model Self-Evolution Engine continuously adapts data strategies to the model's evolving capability state. The Task-Conditioned Adaptive Training Strategy uses task tokens to activate lightweight low-rank residuals over a shared backbone, separating updates from heterogeneous output formats while retaining shared embodied knowledge. Across a systematic evaluation on twelve benchmarks covering three core competencies and five capability dimensions, ABot-ER achieves state-of-the-art overall performance across perception, planning, and execution within a unified parametric framework, demonstrating that breadth and depth can coexist in unified embodied reasoning.

cs.AI↗

arXiv2026

dMRI-F: A Foundation Model for Generalizable Diffusion MRI Analysis from Sparse Acquisitions

Diffusion MRI (dMRI) probes water diffusion within the brain, providing unique information about tissue microstructure and white matter connectivity. High-quality dMRI enables advanced and accurate analyses but demands dense acquisitions, resulting in long scan times and hardware constraints that are often infeasible. Further, dMRI requires dedicated computational methods to support diverse analysis tasks (e.g., parcellation, registration, and synthesis) for both neuroscientific and clinical applications. Here, we present dMRI-F, a foundation model that unifies dMRI data enhancement and downstream tasks across diverse acquisitions and populations, while requiring only minimal acquisition input. dMRI-F is pre-trained with a q-space masked reconstruction task: predicting densely sampled multi-shell data from only six volumes. It learns generalizable latent feature representations of dMRI data, which serve as a core foundation for adapting to diverse downstream tasks, including brain parcellation, brain registration, and cross-modal synthesis. Across nine independently acquired datasets, we demonstrate that dMRI-F outperforms state-of-the-art methods with robust generalization across acquisitions, populations, and tasks. Our results demonstrate dMRI-F's versatility as a general-purpose framework that enables diverse dMRI applications from low-cost, sparse acquisitions.

cs.CV↗

arXiv2026

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation without accounting for the dependency chains through which memories enable the creation of future memories. We introduce MemQ, which applies TD($λ$) eligibility traces to memory Q-values, propagating credit backward through a provenance DAG that records which memories were retrieved when each new memory was created. Credit weight decays as $(γλ)^d$ with DAG depth $d$, replacing temporal distance with structural proximity. We formalize this setting as an Exogenous-Context MDP, separating externally supplied tasks from the evolving memory store, and represent retrieval-set values by a first-order mean of per-memory values plus an explicit approximation residual. Across five interaction, code-generation, and agentic benchmarks, MemQ improves average held-out, final runtime, and cumulative success rates over the baseline with the highest average for each metric by 2.53, 4.23, and 2.13 percentage points, respectively. Ablations on LiveCodeBench, BFCL, and DSBench support the benefit of bootstrapping and multi-depth credit propagation. Analyses of Q-values and runtime learning show that learned memory values are associated with subsequent success and that MemQ retains more of its historical task coverage. We also explore the limits of MemQ's benefits using multiple-choice reasoning tasks, where limited interaction offers fewer opportunities to reuse procedural experience. Code is available at https://github.com/jwliao-ai/MemQ.

cs.AI↗

arXiv2026

Sera: Semantic Representation Aggregation with Knowledge and LLM for Reliable and Interpretable Battery Health Forecasting

Battery state of health (SoH) forecasting is important for battery management, but remains challenging due to nonlinear degradation and heterogeneity across batteries. Existing data-driven approaches primarily use temporal models to learn from numerical battery time series, and higher-level degradation characteristics are often not explicitly represented. These characteristics, however, can provide degradation guidance to support reliable forecasting and make the influence of degradation more interpretable. In this paper, we propose Sera, a semantic representation aggregation framework that complements temporal modelling with degradation semantics. Guided by battery domain expertise, Sera extracts degradation semantics from time series and constructs two complementary representations using rule-based knowledge and LLM-based interpretation. The representations are independently encoded and integrated with the representation learned by temporal models through gated aggregations. Experiments on the mainstream benchmark across multiple prediction horizons and different temporal models show that Sera consistently improves forecasting performance, achieving up to a 37.3% reduction in prediction error over the temporal baseline and enhanced generalizability. Counterfactual analysis examines how forecasts respond to changes in degradation semantics to assess interpretability. The results show that prediction responses are consistent with the meanings of key degradation descriptors across tested horizons. Together, these findings demonstrate that structured degradation semantics and effective aggregation can improve forecasting accuracy and support reliable and interpretable battery health forecasting for advanced battery management.

cs.LG↗

arXiv2026

Decoupling Trap States in Amorphous Oxide Semiconductor Transistor Using a Conductive-Semiconducting-Conductive MOS Structure

We propose a novel amorphous oxide semiconductor (AOS)-based conductive-semiconducting-conductive (CSC) MOS test structure to effectively sense, discriminate, and analyze distinct trap-induced conductance losses in AOS transistors. In conventional test structures, non-ideal metal-AOS contacts convolute the conductance loss generated by various trap states. The CSC architecture mitigates these contact-related artifacts, enabling the decoupling of interface states and shallow states. Furthermore, the contributions from leakage, series resistance, and device-geometry effects are identified and calibrated. Our results yield bias-resolved trap profiles and reveal three distinct regimes: (1) In the depletion region, interface states dominate the conductance loss. These states exhibit sub-microsecond time constants and their density increases slightly with deeper depletion, which is associated with donor-like states. (2) From weak to moderate accumulation, shallow states become the primary contributor, displaying a Gaussian-like volumetric density-of-states distribution with response times spanning from microseconds to nanoseconds. (3) In the strong accumulation regime, interface states regain dominance with an increased state quantity, while their time constants remain invariant. These bias-resolved profiles clarify how different trap populations impact AOS transistors under distinct operating conditions, providing intuitive metrics for understanding reliability degradation. Consequently, the CSC structure offers a simple, scalable, and robust platform for trap characterization in AOS transistors.

cond-mat.mtrl-sci↗

arXiv2026

Simulation and Deep Learning Inversion for Full-sky Energetic Neutral Atom Imaging at the Heliospheric Boundary

The distribution of energetic neutral atom (ENA) differential flux density at the heliospheric boundary is the key to revealing the interaction mechanism between the solar wind and the interstellar medium. The Helios ENA Rapid Mapper (HERMA) is a pre-research project for a new ENA detection concept and technical principle, which is designed to provide technical support for refined detection with its advantages of wide energy range coverage and high spatial resolution. To verify the high spatiotemporal resolution rapid imaging capability of the HERMA, this study restored the particle response characteristics of the HERMA (spatial modulation grid + 256-pixel linear array silicon detector) based on Geant4 simulation, and we compared the performance of the traditional inversion algorithm with the convolutional neural network (CNN) inversion algorithm using INCA data as the benchmark. The results show that under different sampling times, the source distribution inverted by the CNN algorithm has a higher degree of agreement with the ideally expected distribution, and the CNN algorithm exhibits better stability and accuracy than the traditional algorithm under the conditions of low signal-to-noise ratio and short staring time. This study provides core technical support for the engineering verification and on-orbit application of the HERMA instrument, fills the technical gap in wide-energy-range and high-resolution ENA detection, and helps to deepen the research on the interaction mechanism between the solar wind and the interstellar medium at the heliospheric boundary.

astro-ph.IM↗

arXiv2026

Tri-path DINO: Feature Complementary Learning for Remote Sensing Multi-Class Change Detection

In remote sensing imagery, multi-class change detection (MCD) is crucial for fine-grained monitoring, yet it has long been plagued by feature ambiguity in change regions, which obscures subtle changes and hinders fine-grained discrimination under complex scene variations and scarce annotations. To address this, we propose the Tri-path DINO architecture, which adopts a multi-path decoupled complementary feature learning strategy to separately capture coarse-grained semantic features and fine-grained target-edge features. Specifically, we employ the DINOv3 pre-trained model as the backbone feature extraction network to learn coarse-grained features. An auxiliary path also adopts a siamese structure, progressively aggregating intermediate features from the siamese encoder to enhance the learning of fine-grained features. Finally, a multi-scale attention mechanism is introduced to augment the decoder network, where parallel convolutions adaptively capture and enhance contextual information under different receptive fields. The proposed method achieves state-of-the-art performance on Gaza-change, SECOND, and LandsatSCD, improving mIoU/$F_{\mathrm{scd}}$ by 1.01\%/2.93\%, 0.67\%/2.84\%, and 1.22\%/1.51\%, respectively, over the best competing method. Grad-CAM visualizations further confirm that the main and auxiliary paths naturally focus on coarse-grained semantic changes and fine-grained structural details, respectively. This synergistic complementarity provides a robust and interpretable solution for advanced change detection tasks, offering a basis for rapid and accurate damage assessment.

cs.CV↗

arXiv2026

Proposal for a multi-ion optical clock with hundreds of ions

Scaling trapped-ion optical clocks to hundreds of ions remains a major challenge due to inhomogeneous frequency shifts in large ion crystals. Here, we propose a circular surface-trap architecture for a multi-ion optical clock with hundreds of ions. The rotational symmetry of the ion crystal suppresses the main sources of inhomogeneity, quadrupole shift.We investigate the feasibility of a clock based on a ring crystal of 400 $^{40}\mathrm{Ca}^{+}$ ions and propose a suitable experimental setup configuration. We have shown that circular configuration of ions leads to suppression by two orders of magnitude of the quadrupole shift comparing to the linear trap. Combined with stray-field compensation and dynamical decoupling techniques, this architecture provides a pathway toward multi-ion optical clocks with fractional frequency uncertainty at the $10^{-18}$ level and an expected 20-fold improvement in frequency stability compared to single ion clocks.

physics.atom-ph↗

arXiv2026

Skill-Aware Diffusion for Generalizable Robotic Manipulation

Robust generalization in robotic manipulation is crucial for robots to adapt flexibly to diverse environments. Existing methods usually improve generalization by scaling data and networks, but model tasks independently and overlook skill-level information. Observing that tasks within the same skill share similar motion patterns, we propose Skill-Aware Diffusion (SADiff), which explicitly incorporates skill-level information to improve generalization. SADiff learns skill-specific representations through a skill-aware encoding module with learnable skill tokens, and conditions a skill-constrained diffusion model to generate object-centric motion flow. A skill-retrieval transformation strategy further exploits skill-specific trajectory priors to refine the mapping from 2D motion flow to executable 3D actions. Furthermore, we introduce IsaacSkill, a high-fidelity dataset containing fundamental robotic skills for comprehensive evaluation and sim-to-real transfer. Experiments in simulation and real-world settings show that SADiff achieves good performance and generalization across various manipulation tasks. Dataset and videos are available at https://sites.google.com/view/sa-diff.

cs.RO↗

arXiv2026

IFEvalCode: Controlled Code Generation

Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed requirements such as coding style, line count, and structural constraints, beyond mere correctness. To address this, the paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs in controlled code generation, ensuring outputs align more closely with human-defined guidelines. The authors further present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages (Python, Java, JavaScript, TypeScript, Shell, C++, and C#), with each sample featuring both Chinese and English queries. Unlike existing benchmarks, IFEvalCode decouples evaluation into two metrics: correctness (Corr.) and instruction-following (Instr.), enabling a more nuanced assessment. Experiments on over 40 LLMs reveal that closed-source models outperform open-source ones in controllable code generation and highlight a significant gap between the models' ability to generate correct code versus code that precisely follows instructions.

cs.CL↗