Qing Li

The paper introduces VULNSCOUT-C, a compact, specialized transformer model that achieves state-of-the-art performance in C code vulnerability detection while maintaining low inference cost, making it practical for real-world development workflows.

The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

The paper proposes AEGIS, a novel diffusion-guided method for injecting adversarial perturbations into the latent space to create generalizable and robust defenses against advanced facial deepfake manipulations.

SecureAFL introduces a robust framework to secure asynchronous Federated Learning against poisoning attacks by detecting anomalous updates, estimating missing client contributions, and using Byzantine-robust aggregation.

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are distinct from inherent LLM flaws.

DCVD proposes a dual-channel cross-modal fusion framework that jointly detects software vulnerabilities and precisely localizes the vulnerable lines, outperforming existing state-of-the-art methods.

MARGIN proposes a margin-aware framework to detect software vulnerabilities by addressing geometric distortions caused by frequency and difficulty imbalances in embedding space, achieving superior performance on imbalanced datasets.

This paper develops an explainable and deployable machine learning system for highly accurate phishing detection across diverse, heterogeneous datasets, achieving up to 99.78% accuracy using transformer models.

This paper characterizes the graph structure, including cycle and path lengths, of Chebyshev permutation polynomials over the ring $\mathbb{Z}_{2^{k_1}3^{k_2}}$, demonstrating strong regularities despite the complexity of the binary and ternary components.

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing state-of-the-art methods.

The paper introduces Battery-Sim-Agent, an LLM-based framework that reframes the difficult inverse problem of battery parameter estimation as a reasoning task, significantly outperforming traditional optimization methods.

The paper proposes FiVeD, a fine-grained verification framework that uses diagnostic reasoning supervision to significantly improve the reliability and performance of Aspect Sentiment Triplet Extraction (ASTE) systems.

The paper introduces WebIGBench, a novel benchmark designed to rigorously evaluate multimodal LLMs' ability to generate code for complex, interactive webpages, addressing the limitations of existing static evaluation methods.

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, outperforming task-agnostic methods.

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals for open-ended reasoning tasks.

The paper proposes a zero-shot reason-then-retrieve pipeline using Qwen3.5-27B to solve the challenging task of composed video retrieval (CoVR-R), achieving high performance on both validation and blind test splits.

Patcher is a post-hoc defense framework that repairs backdoored large language models by localizing hidden triggers and patching the model using only a single reported failure case.