Li Li

The paper proposes TRIP-RAG, a dynamic anonymization framework that selectively anonymizes sensitive entities in knowledge bases used for RAG, significantly improving utility while maintaining strong privacy protection.

The paper proposes R-CoT, a reasoning-layer watermarking framework that embeds ownership watermarks directly into the stable reasoning path of LLMs, achieving high robustness against perturbations.

Misrouter introduces an input-only adversarial framework to exploit the routing mechanisms of Mixture-of-Experts (MoE) LLMs, enabling unsafe behavior induction against remotely hosted, black-box services.

This paper introduces personalized mechanisms for estimating streaming statistics under $w$-event personalized differential privacy, significantly improving accuracy compared to existing methods.

The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent semantics rather than injecting malicious content.

KLineage introduces a novel method to teach LLMs when and how to apply GPU kernel optimizations by reverse-engineering expert kernel lineages, resulting in superior optimization skills compared to existing baselines.

The paper proposes a unified geodesic framework that combines tangent-constrained priors with curvature regularization to improve the robustness of image segmentation, especially for complex shapes.

This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider cost and usability alongside success rates.

The paper proposes PC-MambaSDE, a physically-constrained continuous-time framework that accurately predicts Remaining Useful Life (RUL) despite irregular sensor observations and ensures physically plausible degradation trajectories.

The paper proposes a compact magnetic tunnel junction (MTJ) device with orthogonal easy axes to implement signed leaky integrate-and-fire (LIF) neurons, enabling bipolar spike generation for enhanced neural network computation.

The paper proposes Astra, an agentic framework that equips Vision-Language Models (VLMs) with the ability to perform spatial reasoning by actively generating and utilizing imagined visual evidence from a world simulator.

The paper introduces RedEdit, an agentic red-teaming framework that demonstrates that malicious images can be easily edited to bypass safety classifiers while retaining their harmful semantics.