arXiv subjects

Mingjun Xiao

Publications and source records attributed to Mingjun Xiao.

11 recordsLinked to original sources

arXiv2026

Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAG

Modern Large Language Model (LLM) serving engines increasingly rely on Retrieval-Augmented Generation (RAG) and non-prefix Key-Value (KV) cache fusion to accelerate long-context, multi-tenant inference. While existing KV cache side-channel attacks require strict linear prefix alignment--rendering them ineffective against real-world RAG queries that contain unique, user-specific private prefixes--we uncover a critical class of structural vulnerabilities inherent to chunk-aware memory scheduling. We demonstrate that the deterministic micro-architectural mechanisms used to align and fuse disjoint memory chunks inadvertently leak a continuous "Step-Wave" timing signature. Exploiting this physical observation, we introduce SpliceLeak, the first end-to-end side-channel attack targeting non-prefix KV cache fusion. SpliceLeak executes a systematic two-phase privacy breach: it first structurally fingerprints the exact length of hidden private prompts, and subsequently manipulates boundary collisions to extract exact semantic content token-by-token. Extensive evaluations on production-grade frameworks (vLLM integrated with LMCache) demonstrate that SpliceLeak achieves up to a 100% extraction success rate in bounded-entropy scenarios. Driven by a deterministic +104 ms hardware latency void, the attack requires as few as 63 requests per token, piercing through realistic continuous batching noise. To resolve the inherent conflict between memory deduplication and security, we propose SpliceDefense, a bipartite mitigation framework consisting of Quantized Chunk Padding (QCP) and Constant-Time Boundary Fusion (CTBF). Our evaluations confirm that SpliceDefense effectively flattens the side-channel signal (Delta TTFT ~ 0) with negligible throughput overhead, preserving the critical benefits of global cache sharing.

cs.CR↗

arXiv2026

MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram Parsing

Parsing chemical reaction diagrams from scientific literature is challenging due to heterogeneous layouts, intertwined visual elements, and the difficulty of integrating recognition and reasoning. Existing vision-language models advance multimodal understanding but still fail on complex diagrams, struggling to maintain spatial coherence and to integrate multidimensional information during reasoning. To address these issues, we propose MACReD, a hierarchical multi-agent framework that coordinates specialized agents for molecular perception, arrow understanding, text extraction, and reaction reconstruction within a unified VLM-guided architecture. The planning and perception layers use flexible, fine-grained detection to handle visual complexity, while the reasoning layer uses a multigraph fusion mechanism to integrate heterogeneous cues and enforce chemically consistent global reasoning. Experiments on the RxnScribe benchmark show that MACReD achieves state-of-the-art performance, with F1 scores of 75.2% and 84.6% under hard and soft match criteria, outperforming the RxnScribe baseline, which obtains 69.1% and 80.0%, respectively. These results demonstrate the robustness of MACReD across diverse diagram layouts, including multi-step and tree-structured reactions.

cs.AI↗

arXiv2026

HillInfer: Efficient Long-Context LLM Inference on the Edge with Hierarchical KV Eviction using SmartSSD

Deploying Large Language Models (LLMs) on memory-constrained AI Personal Computers (AIPCs) enables low-latency, privacy-preserving inference, but long-context generation is fundamentally bottlenecked by the linearly growing Key-Value (KV) cache. While dynamic KV eviction mitigates this memory wall, existing offloading strategies either trigger crippling PCIe I/O bottlenecks on standard SSDs or suffer from FPGA resource exhaustion by forcing compute-intensive exact attention on a single, weak Computational Storage Drive (CSD). In this paper, we propose HillInfer, a CSD-assisted KV eviction framework that introduces a paradigm shift: offloading strictly lightweight token importance evaluation to a single CSD (e.g., SmartSSD) on AIPCs. To fully capitalize on this lightweight offloading strategy, HillInfer orchestrates a Hierarchical KV Cache Manager (HKM) that leverages temporal locality and dynamic token hit rates to physically partition cache pools, thereby eliminating cross-device I/O thrashing. Additionally, we design an Adaptive Prefetch-based Pipeline (APP) that adaptively balances the evaluation workload between the host CPU and the SmartSSD, effectively masking the heterogeneous straggler effect. Finally, we introduce a CSD-based Evaluation Configuration (CEC) to enable resource-efficient near-data processing on the FPGA. Extensive experiments on a commodity AIPC demonstrate that HillInfer achieves up to an 8.56$\times$ speedup over state-of-the-art baselines, delivering low-latency, I/O-efficient long-context inference without sacrificing model accuracy.

cs.AR↗

arXiv2026

CooperLLM: Cloud-Edge-End Cooperative Federated Fine-tuning for LLMs via ZOO-based Gradient Correction

Large Language Models (LLMs) perform well on many NLP tasks, but fine-tuning them on resource-constrained mobile devices is challenging due to high memory and computation costs, despite growing demands for privacy-preserving personalization. Federated Learning (FL) enables local-data training, yet existing methods either rely on memory-intensive backpropagation or use zeroth-order optimization (ZOO), which avoids backward passes but suffers from slow convergence and degraded accuracy. We propose CooperLLM, a cloud-assisted edge-end cooperative federated fine-tuning framework that combines ZOO on mobile devices with cloud-guided gradient rectification. Mobile clients perform lightweight ZOO updates on private data, while the cloud fine-tunes on auxiliary public data using backpropagation and injects guided perturbations to rectify local updates, improving convergence and accuracy without violating privacy. To address system bottlenecks, CooperLLM introduces pipeline scheduling and adaptive compression to overlap computation and communication and reduce memory usage. Experiments on multiple Transformer models and datasets show that CooperLLM reduces on-device memory by up to $86.4\%$, accelerates convergence by $8.8 \times$, and improves accuracy by up to 10 percentage points over state-of-the-art ZOO-based baselines.

cs.LG↗

arXiv2025

Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents

Automated paper reproduction has emerged as a promising approach to accelerate scientific research, employing multi-step workflow frameworks to systematically convert academic papers into executable code. However, existing frameworks often lack mechanisms to verify and refine the outputs at each generation step, or rely heavily on manually designed prompts for self-refinement, which limits their adaptability and scalability. To address these limitations, we propose a prompt-free collaborative agent framework that automatically enhances the quality of paper-to-code generation. Our approach employs two collaborative agents: a verification agent that examines whether the outputs at each step satisfy the requirements specified in the corresponding system prompt, and a refinement agent that revises the outputs based on the identified issues. Unlike previous methods that require human experts to craft specific refinement prompts for each step, our framework achieves automatic verification and improvement by leveraging only the original system prompts. We integrate our collaborative agents into the Paper2Code framework and conduct comprehensive experiments on PaperBench Code-Dev and Paper2CodeBench datasets. Experimental results demonstrate that our approach significantly improves the accuracy and completeness of reproduced code, achieving performance gains of approximately 15\% and 13\%, respectively, compared to the baseline without our agents. Furthermore, comparative experiments against Self-Refine validate the robustness and consistency of our prompt-free approach across different datasets.

cs.AI↗

arXiv2025

SFedKD: Sequential Federated Learning with Discrepancy-Aware Multi-Teacher Knowledge Distillation

Federated Learning (FL) is a distributed machine learning paradigm which coordinates multiple clients to collaboratively train a global model via a central server. Sequential Federated Learning (SFL) is a newly-emerging FL training framework where the global model is trained in a sequential manner across clients. Since SFL can provide strong convergence guarantees under data heterogeneity, it has attracted significant research attention in recent years. However, experiments show that SFL suffers from severe catastrophic forgetting in heterogeneous environments, meaning that the model tends to forget knowledge learned from previous clients. To address this issue, we propose an SFL framework with discrepancy-aware multi-teacher knowledge distillation, called SFedKD, which selects multiple models from the previous round to guide the current round of training. In SFedKD, we extend the single-teacher Decoupled Knowledge Distillation approach to our multi-teacher setting and assign distinct weights to teachers' target-class and non-target-class knowledge based on the class distributional discrepancy between teacher and student data. Through this fine-grained weighting strategy, SFedKD can enhance model training efficacy while mitigating catastrophic forgetting. Additionally, to prevent knowledge dilution, we eliminate redundant teachers for the knowledge distillation and formalize it as a variant of the maximum coverage problem. Based on the greedy strategy, we design a complementary-based teacher selection mechanism to ensure that the selected teachers achieve comprehensive knowledge space coverage while reducing communication and computational costs. Extensive experiments show that SFedKD effectively overcomes catastrophic forgetting in SFL and outperforms state-of-the-art FL methods.

cs.LG↗

arXiv2025

DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation

Nuclear Magnetic Resonance (NMR) spectroscopy is a central characterization method for molecular structure elucidation, yet interpreting NMR spectra to deduce molecular structures remains challenging due to the complexity of spectral data and the vastness of the chemical space. In this work, we introduce DiffNMR, a novel end-to-end framework that leverages a conditional discrete diffusion model for de novo molecular structure elucidation from NMR spectra. DiffNMR refines molecular graphs iteratively through a diffusion-based generative process, ensuring global consistency and mitigating error accumulation inherent in autoregressive methods. The framework integrates a two-stage pretraining strategy that aligns spectral and molecular representations via diffusion autoencoder (Diff-AE) and contrastive learning, the incorporation of retrieval initialization and similarity filtering during inference, and a specialized NMR encoder with radial basis function (RBF) encoding for chemical shifts, preserving continuity and chemical correlation. Experimental results demonstrate that DiffNMR achieves competitive performance for NMR-based structure elucidation, offering an efficient and robust solution for automated molecular analysis.

physics.chem-ph↗

arXiv2025

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

Advanced Large Language Models (LLMs) have achieved impressive performance across a wide range of complex and long-context natural language tasks. However, performing long-context LLM inference locally on a commodity GPU (a PC) with privacy concerns remains challenging due to the increasing memory demands of the key-value (KV) cache. Existing systems typically identify important tokens and selectively offload their KV data to GPU and CPU memory. The KV data needs to be offloaded to disk due to the limited memory on a commodity GPU, but the process is bottlenecked by token importance evaluation overhead and the disk's low bandwidth. In this paper, we present LeoAM, the first efficient importance-aware long-context LLM inference system for a single commodity GPU with adaptive hierarchical GPU-CPU-Disk KV management. Our system employs an adaptive KV management strategy that partitions KV data into variable-sized chunks based on the skewed distribution of attention weights across different layers to reduce computational and additional transmission overheads. Moreover, we propose a lightweight KV abstract method, which minimizes transmission latency by storing and extracting the KV abstract of each chunk on disk instead of the full KV data. LeoAM also leverages the dynamic compression and pipeline techniques to further accelerate inference. Experimental results demonstrate that LongInfer achieves an average inference latency speedup of 3.46x, while maintaining comparable LLM response quality. In scenarios with larger batch sizes, it achieves up to a 5.47x speedup.

cs.OS↗

arXiv2025

AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers

Machine Learning (ML) research is spread through academic papers featuring rich multimodal content, including text, diagrams, and tabular results. However, translating these multimodal elements into executable code remains a challenging and time-consuming process that requires substantial ML expertise. We introduce ``Paper-to-Code'' (P2C), a novel task that transforms the multimodal content of scientific publications into fully executable code repositories, which extends beyond the existing formulation of code generation that merely converts textual descriptions into isolated code snippets. To automate the P2C process, we propose AutoP2C, a multi-agent framework based on large language models that processes both textual and visual content from research papers to generate complete code repositories. Specifically, AutoP2C contains four stages: (1) repository blueprint extraction from established codebases, (2) multimodal content parsing that integrates information from text, equations, and figures, (3) hierarchical task decomposition for structured code generation, and (4) iterative feedback-driven debugging to ensure functionality and performance. Evaluation on a benchmark of eight research papers demonstrates the effectiveness of AutoP2C, which can successfully generate executable code repositories for all eight papers, while OpenAI-o1 or DeepSeek-R1 can only produce runnable code for one paper. The code is available at https://github.com/shoushouyu/Automated-Paper-to-Code.

cs.SE↗

arXiv2020

On Efficient and Scalable Time-Continuous Spatial Crowdsourcing -- Full Version

The proliferation of advanced mobile terminals opened up a new crowdsourcing avenue, spatial crowdsourcing, to utilize the crowd potential to perform real-world tasks. In this work, we study a new type of spatial crowdsourcing, called time-continuous spatial crowdsourcing (TCSC in short). It supports broad applications for long-term continuous spatial data acquisition, ranging from environmental monitoring to traffic surveillance in citizen science and crowdsourcing projects. However, due to limited budgets and limited availability of workers in practice, the data collected is often incomplete, incurring data deficiency problem. To tackle that, in this work, we first propose an entropy-based quality metric, which captures the joint effects of incompletion in data acquisition and the imprecision in data interpolation. Based on that, we investigate quality-aware task assignment methods for both single- and multi-task scenarios. We show the NP-hardness of the single-task case, and design polynomial-time algorithms with guaranteed approximation ratios. We study novel indexing and pruning techniques for further enhancing the performance in practice. Then, we extend the solution to multi-task scenarios and devise a parallel framework for speeding up the process of optimization. We conduct extensive experiments on both real and synthetic datasets to show the effectiveness of our proposals.

cs.DB↗

arXiv2015

Nearly Optimal Probabilistic Coverage for Roadside Advertisement Dissemination in Urban VANETs

Advertisement disseminations based on Roadside Access Points (RAPs) in vehicular ad-hoc networks (VANETs) attract lots of attentions and have a promising prospect. In this paper, we focus on a roadside advertisement dissemination, including three basic elements: RAP Service Provider (RSP), mobile vehicles and shops. The RSP has deployed many RAPs at different locations in a city. A shop wants to rent some RAPs, which can disseminate advertisements to vehicles with some probabilites. Then, it tries to select the minimal number of RAPs to finish the advertisement dissemination, in order to save the expenses. Meanwhile, the selected RAPs need to ensure that each vehicle's probability of receiving advertisement successfully is not less than a threshold. We prove that this RAP selection problem is NP-hard. In order to solve this problem, we propose a greedy approximation algorithm, and give the corresponding approximation ratio. Further, we conduct extensive simulations on real world data sets to prove the good performance of this algorithm.

cs.NI↗