TrafficMoE proposes a Disentangle-Filter-Aggregate (DFA) framework using sparse Mixture-of-Experts to improve encrypted traffic classification by separating header and payload features and adaptively…

ConMoE proposes a train-free method for compressing Mixture-of-Experts (MoE) models by consolidating the large expert pool into a smaller set of reusable prototypes and deterministically remapping all…

dMoE proposes a block-level Mixture-of-Experts (MoE) framework for Diffusion Large Language Models (dLLMs) that aggregates token-level expert distributions into a unified block-level distribution, sig…

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 servi…

The paper proposes DAMPER, a domain-aware framework that autonomously extracts and rewrites private information from text while providing rigorous differential privacy guarantees, significantly improv…

This paper proposes two post-processing techniques, random selection and linear combination, to construct a model that satisfies any desired differential privacy level without retraining, given a set…

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

RouteScan introduces a non-intrusive framework that audits the safety of Mixture-of-Experts (MoE) LLMs by analyzing low-level GPU expert routing telemetry, achieving high accuracy even on unseen harmf…

The paper analyzes the routing behavior of Mixtral MoE under benign and harmful prompts using activation and gradient signals, finding that safety-relevant routing is subtle, depth-dependent, and dist…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

MASCing is a novel framework that enables flexible, non-retraining reconfiguration of Mixture-of-Experts (MoE) models for specific safety objectives by applying activation steering masks to control ex…

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…

The paper introduces 'mixture mechanisms,' a novel class of additive noise mechanisms that achieve approximate differential privacy by mixing multiple Gaussian distributions, resulting in lower noise…

The paper introduces 'mixture mechanisms,' a novel class of additive noise mechanisms that achieve differential privacy for real-valued queries, significantly reducing noise compared to the standard G…

The paper proposes DP-LAC, a novel lightweight adaptive clipping technique for differentially private federated fine-tuning, which efficiently estimates and adapts the clipping threshold without consu…

This paper proposes a new router redesign for Mixture-of-Experts models using Manifold Power Iteration to align router rows with the principal singular directions of associated experts.

The paper introduces ActInv and PAF to systematically analyze and quantify privacy leakage from intermediate activations during split inference of LLMs, proposing PriPert for enhanced defense.

MESA is a targeted alignment framework that decentralizes safety responsibilities across multiple experts in Mixture-of-Experts (MoE) LLMs using Optimal Transport theory, thereby improving safety robu…

FPMoE introduces a sparse Mixture-of-Experts (MoE) architecture to improve functional code generation across multiple functional programming languages, achieving state-of-the-art performance with fewe…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…