arXiv subjects

Jian Weng

Publications and source records attributed to Jian Weng.

At least 19 recordsLinked to original sources

arXiv2026

A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation

Modern GPUs increasingly integrate Tensor Cores into the execution pipeline. Although aggregate tensor throughput continues to grow, aided by an operand supply that has evolved from register-based in Ampere to redundancy-free, memory-based in Hopper and Blackwell, efficiently orchestrating the complete tensor compute pipeline for the modern AI workloads remains challenging. We identify the fundamental bottlenecks as fixed parallelism and coarse-grained scheduling, both of which are exposed by modern AI workloads that interleave diverse non-GEMM operations with GEMM. To orchestrate tensor computation efficiently, we propose FIBER, a new architecture that extends the GPU SIMT (single instruction, multiple thread) model. Its basic execution instance, the \emph{fiber}, is decoupled from private register ownership, carrying only minimal control state while accessing an SM's registers through a shared view. This enables dynamic parallelism scaling, fine-grained register-level dataflow scheduling, and offers a redundancy-free alternative for matrix operand supply. We extend the ISA, microarchitecture, and compiler to realize shared-register addressing, conflict-free operand delivery, and fiber-based program mapping. Under a typical mixed-precision LLM serving scenario, FIBER achieves a 2.25x end-to-end speedup on Ampere (1.15x for the original FP16 computation), with 1.8x and 2.09x on Hopper and Blackwell respectively, and kernel-level gains up to 2.49x.

cs.AR↗

arXiv2026

Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment. Although Dadu-Corki, a dedicated accelerator for efficient embodied AI, has been introduced, it does not exploit the inherent interaction patterns between the robot and its environment, which results in a relatively short predicted action length. We observe that robotic environments naturally alternate between active states-where precise actions are crucial-and inactive states-where actions have limited impact on task success. This insight enables a new scheduling opportunity: long-action-length speculative prediction in inactive states, paired with selective verification in active states. We propose SpecVLA, an algorithm-system co-design framework that adaptively balances action length, inference latency, and task reliability. On the algorithm side, SpecVLA introduces a state-aware VLA inference execution paradigm and a hardware-friendly construction of a smaller verification model (sVLA) using differential residuals and block-wise mixed-precision quantization. On the system side, we develop a heterogeneous architecture consisting of a GPU and a robotic-specific hardware module, along with a speculative dataflow that decouples VLA and sVLA through parallel execution. Comprehensive evaluations on OpenVLA and RDT across LIBERO and ManiSkill benchmarks show that SpecVLA reduces end-to-end latency significantly while preserving task success rate. By enabling long-action-length speculative prediction with timely verification, SpecVLA achieves real-time robotic manipulation with both high efficiency and reliability.

cs.RO↗

arXiv2026

From Neural Intent to Cryptographic Authorization: Securing AI-Driven Enterprise Workflows

The rapid adoption of artificial intelligence (AI)-driven workflows is transforming high-consequence government and enterprise systems into language-based, tool-using and increasingly autonomous infrastructures. While these workflows can delegate planning autonomously, security-critical execution should be strictly mediated. Conventional identity management services authenticate who may invoke a primitive, but remain agnostic to which workflow steps are authorized at runtime. An AI-driven workflow can still be hijacked by injection attacks into executing malicious actions that satisfy identity checks yet violate user intent. We propose Neural Cryptographic Services (NCS), a neuro-symbolic security enforcement plane interposed between neural planners and privileged tools. NCS decouples cognitive planning from execution authority: an untrusted neural planner drafts structured plans, while a deterministic symbolic controller gates execution using an offline-signed, hash-chained instruction stream. Specifically, NCS validates cryptographic signatures and hash chains incrementally, releasing a single instruction template at a time, and admitting a tool call only when its proposed parameters satisfy the constraints of the signed template. Out-of-order or altered tool calls fail-closed, and state transitions are logged for post-hoc auditing. NCS does not attempt to prevent neural planner compromise under injection; it guarantees that a compromised planner cannot dispatch actions outside the authorization. We evaluate NCS using AgentDojo, a custom argument-hijacking dataset, adaptive adversarial instructions, and TheAgentCompany. NCS drives attack success rates to near zero while preserving acceptable utility on benign workflows.

cs.CR↗

arXiv2026

GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design

Modern LLM (large language model) workloads increasingly rely on optimized GPU kernels through hardware-software co-design. These kernels achieve high-performance through fine-grained dependency scheduling and computation-memory overlap. As such, they incur new challenges on existing GPU performance models. Instruction-driven simulators are costly to adapt to evolving architectures, while analytical models are too coarse to capture kernels' characteristics. We propose GPU-Tile-Sim, a tile-centric GPU simulation framework for LLM hardware-software co-design. The key insight is that modern LLM kernel performance is governed less by individual instruction latency than by the dependency structure that controls execution order and overlap. Accordingly, GTSim represents kernel execution as a warp-level tile graph whose nodes capture tile-level operations and whose edges encode data and ordering constraints. Using this representation, we design an automatic tile-graph frontend and a graph-driven simulation backend. We evaluate GTSim on representative GEMM, attention, and end-to-end LLM inference workloads. On A100 and H100 across both conventional and highly optimized kernels, GTSim achieves high performance-modeling accuracy (MAPE, Mean Absolute Percentage Error, 1.22%--8.71%). We further extend GTSim to Blackwell with preliminary validation, and demonstrate its effectiveness in analyzing software and architectural design choices.

cs.DC↗

arXiv2026

A Large-Scale Sparse Multiobjective Optimization Algorithm Based on Optimal Performance Scores

Large-scale sparse multiobjective optimization problems (LSSMOPs) involve a large number of decision variables and Pareto optimal solutions with only a few nonzero variables. However, as the number of decision variables grows, it becomes increasingly challenging to accurately identify the nonzero variables, and optimization performance is adversely affected. To address these issues, this paper proposes an evolutionary algorithm for LSSMOPs. Specifically, we propose a new initialization method capable of generating scores that accurately reflect the importance of variables, and an initial mask vector template that can locate nonzero variables. This leads to the generation of a high-quality initial population. Additionally, this paper introduces a new strategy to calculate the mutation probability for each variable and a novel optimization for real variables based on the Pareto-guided normal distribution, enabling the population to avoid being trapped in local optima and quickly converge to the global optimum. Experimental results from eight benchmark problems and three real-world applications demonstrate that the proposed algorithm achieves superior performance compared with state-of-the-art algorithms.

cs.NE↗

arXiv2026

Affix Cache for Diffusion Large Language Models

Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding and bidirectional context modeling, but efficient inference remains challenging. Unlike autoregressive systems, whose key-value (KV) cache can be reused for shared prefixes, DLLMs couple the KV states of shared context tokens with evolving generated tokens through bidirectional attention, making naive cache reuse stale while full recomputation is expensive. We present ACache, an affix-oriented cache reuse mechanism for shared text spans in DLLMs beyond prefixes. ACache identifies a small request-specific subset of critical affix tokens, called Anchor Tokens, by measuring their influence on masked generation tokens, and selectively recomputes the KV states of only these tokens while reusing the remaining affix cache. Built on Fast-dLLM, ACache recovers the accuracy loss caused by direct affix-cache reuse across different settings when recomputing around 20% of affix tokens. We also build a shared-prefix prototype on top of the Nano-vLLM engine, showing that ACache reduces recompute latency by up to 55.7% and improves end-to-end throughput by up to 1.68$\times$.

cs.CL↗

arXiv2026

Cache-Resident LLM Inference in GB-Scale Last-Level Caches

Large language model (LLM) inference is increasingly dominated by data movement across the memory hierarchy. Recent 3D-stacked cache technologies have enabled GB-scale last-level caches in modern server CPUs, making it possible to keep reusable model weights on chip and exploit cache bandwidth and latency. Achieving this regime is not straightforward: deeper pipelining for weight residency increases in-flight requests and KV-cache footprint, while cache-resident operators make operator-boundary synchronization a visible bottleneck. We present a cache-resident execution model for inference on hierarchical-memory clustered systems. The model separates weight-centric operators from attention and KV-cache management into dedicated resource domains, keeping reusable weights cache-resident while scaling KV capacity independently of pipeline depth. It also relaxes synchronization from operator boundaries to true sub-operator dependencies, reducing coordination overhead in the cache-resident regime. We instantiate this model on a multi-socket CPU cluster with a weight-attention decoupled architecture, locality-aware placement, and a specialized static runtime. The prototype substantially outperforms equally provisioned llama.cpp. On deployed Llama-3.2-3B and Llama-2-7B configurations, it achieves 2.04x-11.51x speedup on time-per-output-token (TPOT). Under a validated analytical model, it further reaches up to 13.9x TPOT speedup across model sizes, context lengths, and batch sizes. These results show that commodity CPUs with GB-scale last-level caches can support efficient LLM inference when execution is organized around cache residency, decoupled state management, and dependency-aware coordination.

cs.AR↗

arXiv2026

Multi-tier Differential Private Query Release

Answering statistical queries over sensitive data under differential privacy (DP) is a common task in many settings, including databases, mobile computing, and data markets. In these scenarios, multiple analysts may issue the same query, while receiving answers generated under different privacy budgets due to differences in trust levels or willingness to pay. Existing approaches for such multi-tier DP queries either incur excessive cumulative privacy loss or suffer from suboptimal utility. In this paper, we propose a framework for multi-tier DP query release that simultaneously bound the cumulative privacy loss by the maximum privacy budget among all queries and achieve optimal utility comparable to that of single-tier mechanisms. Our framework applies to different classes of DP mechanisms. For noise-adding mechanisms (e.g., count queries with the two-sided Geometric mechanism in the curator model), we develop a general solution based on the characteristic functions of noise distributions. For other mechanisms (e.g., count queries under the local DP model with the Subset mechanism), we design mechanism-specific primitives for budget transformation and introduce a template-based strategy that attains optimal utility across different privacy regimes. Experimental results demonstrate the effectiveness of our framework.

cs.CR↗

arXiv2026

Steering LLM Viewpoints through Fabricated Evidence Injection

As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cognitive vulnerability in LLMs: their tendency to uncritically trust external context when presented with fabricated evidence bearing markers of credibility. We introduce Ghostwriter, a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries. Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable, while even frontier classifier-guarded models (e.g., GPT-5.4) reduce but do not eliminate the attack. Building on this, we explore multiple defense strategies, among which a tailored safety policy enables gpt-oss-safeguard to achieve 81% detection rate.

cs.CR↗

arXiv2026

PriSrv: Privacy-Enhanced and Highly Usable Service Discovery in Wireless Communications

Service discovery is essential in wireless communications. However, existing protocols provide limited privacy protection, leaking sensitive device information and opening routes to network attacks. This paper proposes a private service discovery protocol, called PriSrv, which enables both service providers and clients to specify fine-grained authentication policies before establishing connections. PriSrv achieves this via a dual-layer matching architecture: an outer layer filters mismatched entities using public attributes, while an inner layer handles mutual authentication using selectively disclosed private attributes. As a core component, we introduce the primitive of anonymous credential-based matchmaking encryption (ACME), which enables dual-layer matching in a single step to achieve bilateral policy control, selective attribute disclosure, and multi-show unlinkability. To instantiate ACME, we design a fast anonymous credential (FAC) scheme providing constant-size credentials and efficient verification. We demonstrate PriSrv's interoperability by integrating it with popular wireless frameworks including EAP, mDNS, BLE, and AirDrop. Detailed formal security proofs and extensive performance evaluations across desktop, laptop, smartphone, and Raspberry Pi platforms demonstrate that PriSrv provides enhanced privacy guarantees with high usability, achieving secure discovery in less than one second on mainstream mobile devices.

cs.CR↗

arXiv2026

PriSrv+: Privacy and Usability-Enhanced Wireless Service Discovery with Fast and Expressive Matchmaking Encryption

Service discovery is a fundamental process in wireless networks, enabling devices to find and communicate with services dynamically, and is critical for the seamless operation of modern systems like 5G and IoT. This paper introduces PriSrv+, an advanced privacy and usability-enhanced service discovery protocol for modern wireless networks and resource-constrained environments. PriSrv+ builds upon PriSrv (NDSS'24), by addressing critical limitations in expressiveness, privacy, scalability, and efficiency, while maintaining compatibility with widely-used wireless protocols such as mDNS, BLE, and Wi-Fi. A key innovation in PriSrv+ is the development of Fast and Expressive Matchmaking Encryption (FEME), the first matchmaking encryption scheme capable of supporting expressive access control policies with an unbounded attribute universe, allowing any arbitrary string to be used as an attribute. FEME significantly enhances the flexibility of service discovery while ensuring robust message and attribute privacy. Compared to PriSrv, PriSrv+ optimizes cryptographic operations, achieving 7.62* faster for encryption and 6.23* faster for decryption, and dramatically reduces ciphertext sizes by 87.33%. In addition, PriSrv+ reduces communication costs by 87.33% for service broadcast and 86.64% for anonymous mutual authentication compared with PriSrv. Formal security proofs confirm the security of FEME and PriSrv+. Extensive evaluations on multiple platforms demonstrate that PriSrv+ achieves superior performance, scalability, and efficiency compared to existing state-of-the-art protocols.

cs.CR↗

arXiv2025

MCI-Net: A Robust Multi-Domain Context Integration Network for Point Cloud Registration

Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle to effectively capture the implicit semantics and structural consistency in point clouds. To address these issues, we propose a multi-domain context integration network (MCI-Net) that improves feature representation and registration performance by aggregating contextual cues from diverse domains. Specifically, we propose a graph neighborhood aggregation module, which constructs a global graph to capture the overall structural relationships within point clouds. We then propose a progressive context interaction module to enhance feature discriminability by performing intra-domain feature decoupling and inter-domain context interaction. Finally, we design a dynamic inlier selection method that optimizes inlier weights using residual information from multiple iterations of pose estimation, thereby improving the accuracy and robustness of registration. Extensive experiments on indoor RGB-D and outdoor LiDAR datasets show that the proposed MCI-Net significantly outperforms existing state-of-the-art methods, achieving the highest registration recall of 96.4\% on 3DMatch. Source code is available at http://www.linshuyuan.com.

cs.CV↗

arXiv2025

SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context

Recent research has focused on using convolutional neural networks (CNNs) as the backbones in two-view correspondence learning, demonstrating significant superiority over methods based on multilayer perceptrons. However, CNN backbones that are not tailored to specific tasks may fail to effectively aggregate global context and oversmooth dense motion fields in scenes with large disparity. To address these problems, we propose a novel network named SC-Net, which effectively integrates bilateral context from both spatial and channel perspectives. Specifically, we design an adaptive focused regularization module (AFR) to enhance the model's position-awareness and robustness against spurious motion samples, thereby facilitating the generation of a more accurate motion field. We then propose a bilateral field adjustment module (BFA) to refine the motion field by simultaneously modeling long-range relationships and facilitating interaction across spatial and channel dimensions. Finally, we recover the motion vectors from the refined field using a position-aware recovery module (PAR) that ensures consistency and precision. Extensive experiments demonstrate that SC-Net outperforms state-of-the-art methods in relative pose estimation and outlier removal tasks on YFCC100M and SUN3D datasets. Source code is available at http://www.linshuyuan.com.

cs.CV↗

arXiv2025

Kernel Representation and Similarity Measure for Incomplete Data

Measuring similarity between incomplete data is a fundamental challenge in web mining, recommendation systems, and user behavior analysis. Traditional approaches either discard incomplete data or perform imputation as a preprocessing step, leading to information loss and biased similarity estimates. This paper presents the proximity kernel, a new similarity measure that directly computes similarity between incomplete data in kernel feature space without explicit imputation in the original space. The proposed method introduces data-dependent binning combined with proximity assignment to project data into a high-dimensional sparse representation that adapts to local density variations. For missing value handling, we propose a cascading fallback strategy to estimate missing feature distributions. We conduct clustering tasks on the proposed kernel representation across 12 real world incomplete datasets, demonstrating superior performance compared to existing methods while maintaining linear time complexity. All the code are available at https://anonymous.4open.science/r/proximity-kernel-2289.

cs.LG↗

arXiv2025

MambaITD: An Efficient Cross-Modal Mamba Network for Insider Threat Detection

Enterprises are facing increasing risks of insider threats, while existing detection methods are unable to effectively address these challenges due to reasons such as insufficient temporal dynamic feature modeling, computational efficiency and real-time bottlenecks and cross-modal information island problem. This paper proposes a new insider threat detection framework MambaITD based on the Mamba state space model and cross-modal adaptive fusion. First, the multi-source log preprocessing module aligns heterogeneous data through behavioral sequence encoding, interval smoothing, and statistical feature extraction. Second, the Mamba encoder models long-range dependencies in behavioral and interval sequences, and combines the sequence and statistical information dynamically in combination with the gated feature fusion mechanism. Finally, we propose an adaptive threshold optimization method based on maximizing inter-class variance, which dynamically adjusts the decision threshold by analyzing the probability distribution, effectively identifies anomalies, and alleviates class imbalance and concept drift. Compared with traditional methods, MambaITD shows significant advantages in modeling efficiency and feature fusion capabilities, outperforming Transformer-based methods, and provides a more effective solution for insider threat detection.

cs.CR↗

arXiv2025

DMFI: A Dual-Modality Log Analysis Framework for Insider Threat Detection with LoRA-Tuned Language Models

Insider threat detection (ITD) poses a persistent and high-impact challenge in cybersecurity due to the subtle, long-term, and context-dependent nature of malicious insider behaviors. Traditional models often struggle to capture semantic intent and complex behavior dynamics, while existing LLM-based solutions face limitations in prompt adaptability and modality coverage. To bridge this gap, we propose DMFI, a dual-modality framework that integrates semantic inference with behavior-aware fine-tuning. DMFI converts raw logs into two structured views: (1) a semantic view that processes content-rich artifacts (e.g., emails, https) using instruction-formatted prompts; and (2) a behavioral abstraction, constructed via a 4W-guided (When-Where-What-Which) transformation to encode contextual action sequences. Two LoRA-enhanced LLMs are fine-tuned independently, and their outputs are fused via a lightweight MLP-based decision module. We further introduce DMFI-B, a discriminative adaptation strategy that separates normal and abnormal behavior representations, improving robustness under severe class imbalance. Experiments on CERT r4.2 and r5.2 datasets demonstrate that DMFI outperforms state-of-the-art methods in detection accuracy. Our approach combines the semantic reasoning power of LLMs with structured behavior modeling, offering a scalable and effective solution for real-world insider threat detection.

cs.CR↗

arXiv2025

A Universal Framework for Large-Scale Multi-Objective Optimization Based on Particle Drift and Diffusion

Large-scale multi-objective optimization poses challenges to existing evolutionary algorithms in maintaining the performances of convergence and diversity because of high dimensional decision variables. Inspired by the motion of particles in physics, we propose a universal framework for large-scale multi-objective optimization based on particle drift and diffusion to solve these challenges in this paper. This framework innovatively divides the optimization process into three sub-stages: two coarse-tuning sub-stages and one fine-tuning sub-stage. Different strategies of drift-diffusion operations are performed on the guiding solutions according to the current sub-stage, ingeniously simulating the movement of particles under diverse environmental conditions. Finally, representative evolutionary algorithms are embedded into the proposed framework, and their effectiveness are evaluated through comparative experiments on various large-scale multi-objective problems with 1000 to 5000 decision variables. Moreover, comparative algorithms are conducted on neural network training problems to validate the effectiveness of the proposed framework in the practical problems. The experimental results demonstrate that the framework proposed in this paper significantly enhances the performance of convergence and diversity of MOEAs, and improves the computational efficiency of algorithms in solving large-scale multi-objective optimization problems.

cs.NE↗

arXiv2025

DPUV4E: High-Throughput DPU Architecture Design for CNN on Versal ACAP

Convolutional Neural Networks (CNNs) remain prevalent in computer vision applications, and FPGAs, known for their flexibility and energy efficiency, have become essential components in heterogeneous acceleration systems. However, traditional FPGAs face challenges in balancing performance and versatility due to limited on-chip resources. AMD's Versal ACAP architecture, tailored for AI applications, incorporates AI Engines (AIEs) to deliver high computational power. Nevertheless, the platform suffers from insufficient memory bandwidth, hindering the full utilization of the AIEs' theoretical performance. In this paper, we present DPUV4E for the Versal architecture, providing configurations ranging from 2PE ($32.6$ TOPS) to 8PE ($131.0$ TOPS). We design two computation units, Conv PE and DWC PE, to support different computational patterns. Each computation unit's data flow efficiently utilizes the data reuse opportunities to mitigate bandwidth bottlenecks. Additionally, we extend the functionality of each PE to utilize AIEs for non-convolutional operations, reducing resource overhead. Experiments on over 50 models show that compared to previous designs, our design provides $8.6\times$ the TOPS/W of traditional FPGA-based DPU designs, while reducing DSP usage by $95.8\%$, LUT usage by $44.7\%$, and latency to $68.5\%$ under single-batch conditions. For end-to-end inference, our design improving throughput by up to $2.2\times$ for depth-wise convolution models and up to $1.3\times$ for standard models.

cs.AR↗