| PICO: Secure Transformers via Robust Prompt Isolation and Cybersecurity Oversight | Apr 26, 2025 | Mixture-of-ExpertsPICO | —Unverified | 0 |
| NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation | Apr 25, 2025 | Code CompletionMixture-of-Experts | —Unverified | 0 |
| Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection | Apr 24, 2025 | Graph AttentionMixture-of-Experts | CodeCode Available | 0 |
| BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts | Apr 24, 2025 | Backdoor AttackMixture-of-Experts | —Unverified | 0 |
| Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images | Apr 21, 2025 | Mixture-of-Experts | CodeCode Available | 1 |
| MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core | Apr 21, 2025 | Mixture-of-Experts | —Unverified | 0 |
| Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification | Apr 21, 2025 | Exemplar-FreeKnowledge Distillation | CodeCode Available | 1 |
| Multi-Type Context-Aware Conversational Recommender Systems via Mixture-of-Experts | Apr 18, 2025 | Mixture-of-ExpertsRecommendation Systems | —Unverified | 0 |
| HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering | Apr 18, 2025 | ClusteringGraph Clustering | —Unverified | 0 |
| D^2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving | Apr 17, 2025 | Mixture-of-ExpertsModel Compression | —Unverified | 0 |
