Sharded blockchains enhance scalability by partitioning the system into parallel shards. However, even with parallel processing, the substantial coordination overhead and suboptimal placement of interdependent contracts lead to significant performance degradation when executing cross-shard transactions (CSTxs). Therefore, efficiently managing costly CSTxs through a dependency-aware placement strategy presents a significant challenge. In this paper, we propose JiangZiya, a dependency-aware smart contract migration mechanism that improves CSTx execution efficiency. We model contract dependencies as a gas-weighted invocation graph to reflect realistic execution costs. Furthermore, we employ a genetic algorithm to optimize contract placement and a dual-mode protocol to execute remaining CSTxs, complemented by a lightweight storage module. Finally, we conduct extensive experiments to compare our work with state-of-the-art baselines on real-world workloads. The evaluation results show that JiangZiya improves throughput by up to 4.2× and reduces latency by up to 74%.

Serverless computing has emerged as a compelling cloud paradigm due to its simplified development model, automatic scalability, and fine-grained billing. While its stateless execution model enables high elasticity and resource efficiency, it poses noteworthy challenges for building complex stateful applications. To bridge this gap, modern serverless platforms rely on external cloud storage systems to manage persistent state, giving rise to stateful serverless computing. However, this decoupled architecture introduces two fundamental limitations: performance bottlenecks caused by frequent remote state accesses, and state reliability issues stemming from function crash retries. We propose Arcus, a high-performance function state I/O system co-designed for both idempotent execution and low-latency access. Arcus integrates two key techniques: CFLog, a coordination-free logging mechanism that eliminates internal ordering overhead while ensuring idempotent function execution, and FCCache, a cache system optimized for the dispersed invocation pattern of serverless workloads, which reduces read/write latency by improving local hit rates for reads and shortening the write path. Compared to the state-of-the-art system Halfmoon, Arcus reduces read/write latency by 80.4% and 87.9%, respectively. In evaluations using three real-world applications, Arcus achieves an average 60.3% reduction in end-to-end request latency, demonstrating its effectiveness for fast and reliable function state I/O.

Large Vision Transformers (ViTs) must often be compressed before they can be deployed on resource-constrained edge devices. However, many edge devices require only part of the *all-classes* knowledge of a pre-trained ViT in their corresponding application scenarios. This is overlooked by existing compression methods. Lightweight models produced by these methods retain a substantial amount of class-irrelevant knowledge and suffer suboptimal performance on target classes. To address this, we analyze the knowledge distribution of ViT and reveal a knowledge disentanglement within it: neurons in the feed-forward network (FFN) modules encode class-specific knowledge, while the multi-head attention (MHA) modules capture class-agnostic patterns. Building on this insight, we introduce Vulcan, a pruning-oriented post-training method for deriving compact class-specific models from a pre-trained ViT under given resource budgets. Vulcan follows a novel *train-then-prune* paradigm, which introduces redundancy into ViTs deliberately by collapsing FFN neurons onto those with the highest class-specific activations and by enforcing low-rankness in MHA weights. This design mitigates the irreversible knowledge loss of direct pruning, so that the post-trained model can be compressed into a compact one with negligible performance loss. Notably, the derived edge ViTs not only achieve significant reductions in size and computation but also even surpass the original ViTs in performance on specific classes. Comprehensive experiments with five base ViTs covering three representative visual tasks on four datasets demonstrate that Vulcan-derived ViTs outperform the base ViTs on class-specific tasks by up to 15.12\% in accuracy, with only 20\%–40\% of their sizes. Compared with state-of-the-art structured pruning methods, Vulcan improves class-specific accuracy by up to 13.92\%. Code is available at [Vulcan](https://anonymous.4open.science/r/Vulcan-4CEB).

The increasing popularity of container technology raises significant challenges in efficiently storing millions of container images in registries to enable fast on-demand image pulling. This is further complicated by (1) registries are geographically distributed, with independent and heterogeneous storage resources; (2) container images are pulled in layers, but can be stored at different levels of granularity, i.e., layer-level or file-level, each with varying storage requirement and pulling latency. To address the above challenges, we propose MIS, a multi-granularity image storage strategy, for distributed registries to determine the storage granularity and schedule image storage collaboratively, aiming to reduce the image pulling latency while improving the storage utilization. We formulate the image storage problem into a nonlinear mixed-integer programming form with NP-hardness by incorporating both layer-level and file-level storage constraints. We propose a low computational complexity algorithm via randomized rounding with a guaranteed approximation ratio. Extensive experimental results demonstrate the effectiveness of our strategy, with image pulling latency reductions of 28.67%, 21.69%, and 28.94% respectively compared to the state-of-the-art solutions.

As submission volumes grow, AI conference peer review increasingly suffers from scale drift and non-comparable scoring: similar rationales can yield markedly different numeric ratings due to subjective calibration and occasional incoherent or strategic scoring, even though scores often strongly influence outcomes. This position paper argues that . The residual between a reviewer’s reported score and the anchor score turns rationale--score misalignment into a measurable signal for targeted escalation. We instantiate an end-to-end pipeline and apply it to OpenReview data from ICLR 2023--2025 to quantify severity/leniency patterns and where misalignment concentrates. We further propose a lightweight post-check---requesting added justification or score revision when residuals are large---and estimate its impact via an offline counterfactual simulation. Finally, we outline an adoption playbook and governance boundaries, emphasizing that the LLM audits scoring coherence rather than replacing human judgment or making accept/reject decisions.

Continuous Approximate Nearest Neighbor Search (ANNS) over real-time vector data streams is an increasingly critical yet underexplored problem. In open-world settings—where data distributions shift, noise accumulates, and concurrent access is common—existing ANNS algorithms, originally designed for static or simplified streaming scenarios, struggle to balance ingestion latency, retrieval quality, and update efficiency. While benchmarks such as ANN-Benchmarks and Big-ANN-Benchmarks have standardized evaluation in static or large-scale settings, they fail to capture the nuanced, high-churn dynamics of real-world streams. We introduce CANDOR-Bench ( C ontinuous A pproximate N earest neighbor search under D ynamic O pen-wo R ld Streams, a benchmarking framework built on Big-ANN-Benchmark to evaluate in-memory ANNS under dynamic, open-world conditions. CANDOR-Bench supports high-frequency ingestion (up to hundreds of thousands of vectors per second), adaptive drift modeling (including modality shifts), stochastic noise injection, and concurrent query-update execution—all without requiring modifications to algorithm code. Across 12 datasets and 19 representative ANNS algorithms, our evaluation reveals that no single ANNS algorithm consistently delivers high recall, throughput, and update efficiency across dynamic open-world scenarios, which challenges assumptions drawn from static benchmarks. This variability reflects deeper trade-offs inherent to streaming settings. For example, smaller update batches improve data freshness but can introduce higher insertion overhead and reduce accuracy. We further observe that throughput in concurrent settings is often constrained by insertion overhead rather than query latency, which highlights a mismatch between streaming workloads and designs originally tuned for offline construction.

Scene Graph Generation (SGG) is pivotal for structured visual understanding, yet it remains hindered by a fundamental limitation: the reliance on fixed, frozen semantic representations from pre-trained language models. These semantic priors, while beneficial in other domains, are inherently misaligned with the dynamic, context-sensitive nature of visual relationships, leading to biased and suboptimal performance. In this paper, we transcend the traditional one-stage v.s. two-stage architectural debate and identify this representational bottleneck as the core issue. We introduce Adaptive Prompt Tuning (APT), a universal paradigm that converts frozen semantic features into dynamic, context-aware representations through lightweight, learnable prompts. APT acts as a plug-in module that can be seamlessly integrated into existing SGG frameworks. Extensive experiments demonstrate that APT achieves +2.7 improvement in mR@100 on PredCls, +3.6 gain in F@100 and up to +6.0 gain in mR@50 in open-vocabulary novel splits. Notably, it achieves this with less than 0.5M additonal parameters (<1.5\% overhead) and reduced 7.8\%-25\% training time, establishing a new state-of-the-art while offering a unified, efficient, and scalable solution for future SGG research. The source code of APT is available at .

Data deduplication, originally designed for cloud storage systems, is increasingly popular in edge storage systems due to the costly and limited resources and prevalent data redundancy in edge computing environments. The geographical distribution of edge servers poses a challenge in aggregating all data storage information for global decision-making. Existing edge data deduplication (EDD) methods rely on centralized cloud control, which faces issues of timeliness and system scalability. Additionally, these methods overlook data popularity, leading to significantly increased data retrieval latency. A promising approach to this challenge is to implement distributed EDD without cloud control, performing regional deduplication with the edge server requiring deduplication as the center. However, our investigation reveals that existing distributed EDD approaches either fail to account for the impact of collaborative caching on data availability or generate excessive information exchange between edge servers, leading to high communication overhead. To tackle this challenge, this paper presents EdgeDup, which attempts to implement effective EDD in a distributed manner. Additionally, to ensure data availability, EdgeDup aims to maintain low data retrieval latency. EdgeDup achieves its goals by: 1) identifying data redundancies across different edge servers in the system; 2) deduplicating data based on their popularity; and 3) reducing communication overheads using a novel data dependency index. Extensive experimental results show that EdgeDup significantly enhances performance, i.e., reducing data retrieval latency by an average of 47.78% compared to state-of-the-art EDD approaches while maintaining a comparable deduplication ratio.

As an emerging distributed computing paradigm, edge computing (EC) brings computing and storage capabilities to the network edge to support low-latency services. Service providers can cache popular data on edge servers to greatly reduce service latency and improve service quality. However, data popularity in EC environments is often dynamic and stochastic. Given the limited storage resources of edge servers, when data popularity changes, data may need to be migrated from edge servers with lower data popularity to those with higher data popularity. Data migration between edge servers can effectively reduce the high transmission costs associated with transferring data from the cloud to the edge. Most existing data migration approaches are designed for static EC environments, assuming that user access patterns and data demands remain constant over time. Even in dynamic EC environments, many approaches oversimplify data popularity by treating it as static, failing to model its fluctuations over time. In realistic EC scenarios, unexpected situations, such as sudden shifts in user preferences for specific data at certain times, can cause significant fluctuations in data popularity, leading to increased data retrieval latency and inefficient storage management. To address this uncertainty, this paper proposes a popularity uncertainty-aware online data migration approach that combines distributed robust optimization and Lyapunov optimization to minimize the data retrieval latency and migration cost for service providers. Specifically, it handles data popularity uncertainty in a data-driven manner through robust optimization. Then, it employs Lyapunov optimization to decompose the continuous optimization problem into multiple single-slot online optimization problems. Extensive experiments on a widely used real-world dataset confirm the effectiveness of this approach and its significant advantages over state-of-the-art approaches.

Most evaluations of External Memory Module assume a static setting: memory is built offline and queried at a fixed state. In practice, memory is streaming: new facts arrive continuously, insertions interleave with retrievals, and the memory state evolves while the model is serving queries. In this regime, accuracy and cost are governed by the full memory lifecycle, which encompasses the ingestion, maintenance, retrieval, and integration of information into generation. We present Neuromem, a scalable testbed that benchmarks External Memory Module under an interleaved insertion-and-retrieval protocol and decomposes its lifecycle into five dimensions including memory data structure, normalization strategy, consolidation policy, query formulation strategy, and context integration mechanism. Using three representative datasets LoCoMo, LONGMEMEVAL, and MemAgentBench, Neuromem evaluates interchangeable variants within a shared serving stack, reporting token-level F1 and insertion/retrieval latency.Overall, we observe that performance typically degrades as memory grows across rounds, and time-related queries remain the most challenging category. The memory data structure largely determines the attainable quality frontier, while aggressive compression and generative integration mechanisms mostly shift cost between insertion and retrieval with limited accuracy gain.

The serverless computing paradigm has emerged as a promising solution to address the resource underutilization and inflexible service scaling in edge environments by decomposing the monolithic application into a serverless workflow. However, existing serverless platforms are primarily designed for cloud data centers, relying on heavyweight isolation mechanisms that are ill-suited for resource-constrained edge computing. These limitations lead to high latency, low deployment density, and restricted parallelism. In this paper, we propose Sonnet, a serverless platform tailored for edge computing, capable of rapidly responding to user requests and supporting efficient and elastic service scaling. Sonnet offers these features by (i) employing lightweight WebAssembly as the execution environment for functions, (ii) leveraging serverless workflow information to optimize function deployment on resource-constrained edge environments, and (iii) providing a function deployment algorithm that achieves dynamic load balancing within the cluster. An extensive evaluation of Sonnet with real-world serverless workflows demonstrates its effectiveness and practical applicability. Compared with SOTA and commonly used edge computing serverless solutions, Sonnet can reduce end-to-end latency by 27% and improve throughput by 2.83x

W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-step denoising trajectory. These difficulties are compounded by Wan2.2-I2V's two-expert Mixture-of-Experts DiT design, whose high-noise and low-noise experts exhibit distinct quantization sensitivities that a single global calibration policy cannot capture. We propose a post-training quantization framework combining SVDQuant-based low-rank outlier compensation, GPTQ-based reconstruction-aware residual weight quantization, and timestep-bin-wise per-layer activation clipping-ratio search conducted independently for each expert. On the OpenS2V-Eval benchmark, our method reduces peak GPU memory by 59.3% relative to the BF16 baseline while incurring only a 0.9% drop in VBench average score and a 2.3% drop in Imaging Quality, demonstrating that expert- and timestep-aware calibration is essential for high-fidelity W4A4 inference on MoE video DiTs.

Mobile edge computing (MEC) is an emerging distributed paradigm where edge servers are deployed near base stations or access points to support low-latency services. The edge user allocation (EUA) problem, which aims to minimize system cost while meeting constraints like data transmission latency, has become a critical challenge for service providers. Existing studies typically focus on static MEC scenarios, assuming predictable latency between users and edge servers. However, network congestion introduces latency uncertainty, which, if not addressed, increases the risk of allocation failures or excessive service latency. This paper addresses the latency uncertainty-aware edge user allocation (uEUA) problem. We model uEUA as an integer programming problem and apply chance-constrained programming to convert uncertain latency into probabilistic constraints, which we then transform into deterministic conditions using Chebyshev's inequality. We propose two methods to solve the problem: BD-uEUA, an exact approach based on Benders decomposition, and LR-uEUA, an approximate method based on linear relaxation. Extensive experiments on a real-world dataset show that BD-uEUA reduces system costs by 19.70% compared to the state-of-the-art method, while LR-uEUA achieves a 3.05% reduction with only 0.09% of the system overhead.

Stream Learning (SL) requires models that can quickly adapt to continuously evolving data, posing significant challenges in both computational efficiency and learning accuracy. Effective data selection is critical in SL to ensure a balance between information retention and training efficiency. Traditional rule-based data selection methods struggle to accommodate the dynamic nature of streaming data, highlighting the necessity for innovative solutions that effectively address these challenges. Recent approaches to handling changing data distributions face challenges that limit their effectiveness in fast-paced environments. In response, we propose StreamFP, a novel approach that uniquely employs dynamic, learnable parameters called fingerprints to enhance data selection efficiency and adaptability in stream learning. StreamFP optimizes coreset selection through its unique fingerprint-guided mechanism for efficient training while ensuring robust buffer updates that adaptively respond to data dynamics, setting it apart from existing methods in stream learning. Experimental results demonstrate that StreamFP outperforms state-of-the-art methods by achieving accuracy improvements of 15.99 compared to baseline models across varying data arrival rates, alongside a training throughput increase of 4.6x.

Deep learning-based source code vulnerability analysis has become a prominent trend in vulnerability detection, offering the capability to automatically extract vulnerability features and reduce manual effort. However, the limited availability of vulnerability data prevents models from comprehensively capturing diverse vulnerability patterns. In addition, the scarcity of samples labeled with specific vulnerability types restricts models to merely identifying the presence of vulnerabilities, without providing fine-grained type information that is crucial for efficient vulnerability diagnosis and remediation. To address these challenges, we propose VulInject, the first automated tool for generating multi-type vulnerable samples for learning-based detection. Our approach extracts edit patterns from existing vulnerability datasets and applies them to benign projects, thereby synthesizing realistic vulnerable code resembling real-world cases. Furthermore, we adopt a hybrid strategy that integrates static analysis with large language models to annotate the generated samples with precise vulnerability types. By augmenting existing datasets with these generated samples, we conduct extensive experiments on state-of-the-art binary and multi-class vulnerability detection models. Results demonstrate substantial performance gains, with binary classification models achieving up to a 13.50% increase in F1 score, and multi-class models improving by 7.65%.

Efficient dynamic graph processing is critical for real-time applications. Recent systems utilize hybrid layouts combining Packed Memory Array (PMA) and Compressed Sparse Row (CSR) structures to balance updating and computing efficiency. However, these systems face key challenges, including costly global copying and traversal during reconstruction, which in turn induce excessive costly rebalancing processes during graph updating, limiting performance under intensive updates. To mitigate these, existing solutions either compromise cache efficiency by relaxing memory contiguity or apply OS-level techniques without exploiting graph structural properties, leaving large optimization space unexplored. In this paper, we propose GRACE, a lightweight extension for PMA-based CSR systems that leverages graph structural properties to improve reconstruction and support efficient updates without sacrificing layout contiguity. Specifically, GRACE incorporates 1) a propertyguided reservation strategy that partitions the PMA into regions and applies tailored methods, minimizing copying and traversal during reconstruction while providing optimized layout for rebalancing, and 2) a cousin-aware rebalancing strategy that assesses the impact of the vertices and confines rebalancing to smaller ranges by exploiting cousin segments of PMA tree, reducing redundant relocation during insertion. We implement GRACE as a modular plugin atop representative dynamic graph processing systems, including PPCSR, Terrace, and VCSR. Experimental results show that GRACE effectively accelerates their reconstruction and achieves substantial improvements in graph updating efficiency while maintaining comparable computing performance.