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
44 results for “keyword:"mean field"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Convergence of Mean-Field Transformers and Bilevel Training Dynamics in the Repulsive Regime▼5.8k2.33
[PDF]SKARL: Kernel Mean-Field Reinforcement Learning for Zero-Shot Population-Size Transfer▼4.3k2.00
[PDF]A Solvable Model of Adaptive Learning Rate Rescaling: Acceleration, Stability & Scaling▼5.8k2.33
[PDF]Root Multiplicity Sets the Finite-Width Edge of Chaos in MLPs and Message-Passing Networks▼5.8k2.33
[PDF]Mean-Field Q-Learning for Heterogeneous Multi-Agent Systems with Convergence Guarantees▼4.3k2.00
[PDF]Beyond Linear and Overcomplete Regimes: A Mean-Field Analysis of Bottleneck Autoencoders▼4.5k2.67
[PDF]Learning Generative Dynamics with Soft Path-Law Constraints: A McKean-Vlasov FBSDE Approach▼5.8k2.33
[PDF]Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer▼1.2k3.00
[PDF]Mean–Covariance Competition Governs Collapse and Multi-Cluster States in Causal Attention Dynamics▼4.3k2.00
[PDF]Graphene: A Lightweight Transformer with Ising Mean-Field Refinement for Image Super-Resolution▼4.3k2.00
[PDF]SpinSCI: Mask-Conditioned Spatial-Temporal Spin Transformer for Video Snapshot Compressive Imaging▲3.0k2.33
[PDF]When Parameter Bounds Limit Learning: Approximation and Estimation in Mean-Field Neural Networks▼3.7k2.25
[PDF]High-Dimensional Dynamics of Mixture-of-Experts: Phase Transitions, Routing, and Specialization▼4.5k2.67
Withdrawn or desk rejected (4)
[PDF]Towards Understanding Specialization in MoE: A Mean-Field Perspective on Routing-Expert DynamicsWithdrawn2.00