En Zhang

GESR introduces a graph-based framework that reconstructs edge semantics from local structural context to detect stealthy malicious communications using only benign training data, achieving high performance on standard datasets.

The paper introduces MT-JailBench, a modular framework for evaluating multi-turn jailbreaks, demonstrating that controlling experimental components like prompt generation and resource budgets is crucial for fair comparison and understanding attack success.

The paper introduces GRIEF, a greybox fuzzer that discovers critical, concurrency-related vulnerabilities in LLM serving systems by treating timed multi-request traces as inputs, finding issues like cache isolation failures and cross-request contamination.

The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.

The paper introduces EBCC, an OCI-compatible runtime architecture that manages composite confidential-computing workloads by integrating TEE-backed execution into the standard container lifecycle.

The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving fast and generalizable detection.

This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these variants.

Reflect-Guard enhances LLM safety classifiers by integrating logical self-reflection, significantly improving detection of sophisticated adversarial jailbreak prompts.

The paper proposes eSpat-B and eSpat+ systems to enable efficient and privacy-preserving distribution statistics analysis on massive, dynamic mobile spatial data.

VFEAgent is a novel multi-agent framework that automates the entire Finite Element Analysis (FEA) workflow, achieving high success rates in generating complete and physically valid simulations directly from multimodal inputs.

The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for large multimodal models.

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Rate (ADR) for a more robust assessment.

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

The paper introduces polynomial representations as a quantitative, distribution-aware metric for measuring model simplicity, demonstrating that the effective degree of this representation is a superior predictor of generalization compared to existing proxies.

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance across diverse tasks.

ElasticMem introduces a novel framework that treats memory as an elastic latent resource, allowing LLM agents to adaptively manage and inject variable-budget memories for improved performance in long-term reasoning tasks.

GIRL-DETR introduces Gradient-Isolated Reinforcement Learning to enhance temporal localization in lightweight Video Moment Retrieval models, achieving high accuracy by decoupling feature representation from metric optimization.

The paper introduces a higher-order network framework to compare observed and simulated human mobility data, demonstrating that while synthetic data is promising, current simulation models have specific limitations regarding path-based movement patterns.

CRAFTQA introduces a novel adaptive, code-driven framework that significantly enhances complex structured data reasoning by dynamically generating custom code functions beyond predefined operations.

IstGPT introduces a novel LLM-based framework for real-time, fine-grained anomaly detection in complex industrial cyber-physical systems, achieving state-of-the-art performance across multiple benchmarks.