NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
421 results for “keyword:"mixture of experts"” in ICLR 2027. 82 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RcMoE: Semantic-Conditioned Retrieval for Efficient MoE Inference on Commodity Edge Devices▲5103.00
[PDF]What Does the Global Model Leave Behind? Client-Conditioned Residual Experts for Federated Learning▲3.0k2.33
[PDF]BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding▼1.2k3.00
[PDF]Spk2ImgMoE: Heterogeneous Mixture-of-Experts for High-Fidelity Spike-to-Image Reconstruction▼5.8k2.33
[PDF]SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining▼4.3k2.00
[PDF]TriHAR: Hierarchical Adaptive Routing of Representations, Modalities, and Cross-modal Interactions for Multimodal Clinical Prediction▲3952.67
[PDF]HeteroLoRA-MoE: Heterogeneous Low-Rank Experts with Diverse Projection Patterns and Efficient GPU Kernels▼4.3k2.00
[PDF]Expert-Level Analog-Digital Mapping of Mixture-of-Experts with Theoretical Generalization Guarantees▼4.5k2.25
[PDF]Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization▼1.2k1.67
[PDF]Mambura: a Mamba-Transformer Hybrid for Unified Multimodal Understanding and Generation▼5.8k2.33
Withdrawn or desk rejected (82)
[PDF]Exploring Expert Concentration for Parameter-efficient Fine-tuning of Mixture-of-Expert LLMsWithdrawn1.67
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00
[PDF]SurroGate: Efficient Text-to-Image Routing via Continuous Generative Profiling in Sparse MoEsDesk rejected
[PDF]Routing by Need, Not by Modality: Demand-Conditioned Sparse Activation for MoE-VLMsWithdrawn1.00