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
51 results for “keyword:"initialization"” in ICLR 2027. 14 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Does the Mask Know Where to Cut? Separating Topology from Weight Placement in Rewiring Nulls▲3.0k2.33
[PDF]Does Energy-Aware Sparsity Allocation Help Dynamic Sparse Training? Leverage, Execution Back Ends, and Stable Regrowth▲5103.00
[PDF]Input Embeddings as a Compositional Pronunciation Interface for Frozen LLM-Based Chinese TTS▼4.3k2.00
[PDF]Beyond Initial Skills: Contrast-Guided Skill Evolution for Robust Learning in LLM Agents▼5.8k2.33
[PDF]UAR-LoRA: Uncertainty-Aware Rank-Adaptive Low-Rank Adaptation for Lifelong Knowledge Editing▼1.2k1.67
[PDF]Ideal Paths: Geometric Approximation of Logistic Gradient Descent Trajectories at Large Initialization▲13k2.33
[PDF]When LoRA Rank Matters in RLVR: Saturation-Gated Scaling and Off-Principal Initialization▼1351.33
[PDF]ScaledGD for Underparameterized Matrix Factorization: Global Convergence and Stepsize Universality▲603.50
[PDF]Identity-Exact Multi-Bias Activations: Breaking Optimization Symmetry Without Changing the Pretrained Function▼1351.33
[PDF]Geometric Supercharger: Data-Informed Hyperbolic Initialization of MLP-based Sparse Neural Networks▲6.3k2.25
[PDF]Initial Spectral Power Predicts Frequency Selection in Grokking and Steers It in Tied MLPs▼1351.33
[PDF]Outcome-Ranked Proposal Tuning: Training LLMs to Transfer Experience Across Bayesian Optimization Tasks▼4.3k2.00
[PDF]Amortized Physics-Informed Learning via Generative Initialization of Radial Basis Functions▲5.4k3.00
[PDF]Just Initialize: A Training-Free Initialization Component for Large-Scale Routing Optimization▼4.3k2.00
[PDF]Prior Subspace Recomposition: A Unified Prior Initialization Framework for Conditional Generation▲3.0k2.50
[PDF]A Lasting Bias of Initialization: How Initialization Shapes Generalization in Vision Transformers▼5.8k2.33
[PDF]Bregman–Gromov–Wasserstein Clustering: Finite-Length Whole-Sequence Convergence and Local Initialization Consistency▼1.2k1.67
[PDF]SAHyper: Breaking the Rank Bottleneck and Rethinking Pretrained Weight Inheritance in Graph Hypernetworks▼5.8k2.33