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
465 results for “keyword:"rts"” in ICLR 2027. 97 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[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
[PDF]ElectrolyteFM: Unifying Electrolyte Property Prediction through Cross-Property Knowledge Learning▲9.2k2.67
[PDF]Square-Root Gradient Routing: Geometrical Understanding of Router Optimization in Sparse MoEs▲9.2k2.67
[PDF]Why This Expert? A Feature-Level Analysis of Routing in Mixture-of-Experts with Sparse Autoencoders▼1.2k1.67
[PDF]LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration▼4.3k2.00
[PDF]CROWN: Conversion to Routed Experts with Output-Aware Width Narrowing for Audio-Video Diffusion▼4.3k2.00
[PDF]Large Language Models as Tutors of Clinical Semantics for Learning Cardiac Representations▼4.5k2.67
[PDF]MMoE: Multi-Level Routing Capacity Allocation for Extremely Sparse Multimodal MoE Inference▲3952.67
[PDF]Direct Spectral Actuation: Prediction-Preserving Expert Differentiation in Mixture-of-Experts▼4.3k2.00
[PDF]The Generator Is the Tracker: Multi-Object Tracking by Painting Persistent Identity Colours▼4.3k2.00
[PDF]CLoRE: Drift-Controlled Continual Learning of LLMs via Expert Expansion with Reservoir Routing▲9.2k2.67
[PDF]UNDERSTANDING MOE INFERENCE ENERGY CONSUMPTION VIA EXPERT ACTIVATION TRAJECTORY ANALYSIS▼1361.33
[PDF]Can we improve the performance of sparse attention in Grouped Query Experts without increasing experts?▲11.00
Withdrawn or desk rejected (97)
[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]The Price of Hidden Assignments: Calibration and Minimax Rates in Pooled CATE LearningWithdrawn1.33
[PDF]SurroGate: Efficient Text-to-Image Routing via Continuous Generative Profiling in Sparse MoEsDesk rejected