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
583 results for “keyword:"gradient"” in ICLR 2027. 106 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Structure Follows Causality: Causally-Aligned Representation Separation Breaks Orthogonal Bullying in Multi-Task Learning▼1361.33
[PDF]Checkable NTK Positivity and Finite-Width Gradient Descent for Scalar- and Vector-Valued PINNs with Strong-Form, Weak-Form, and Nonlocal Linear Constraints▼4.3k2.75
[PDF]Where Should Suppressed Probability Go? One-Step Lookahead KL Routing for On-Policy Distillation▲6.1k2.00
[PDF]From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models▼1.2k1.67
[PDF]Multi-Query Associative Correction: Enriching the Readout Interface for History-Conditioned Low-Rank Adaptation▼4.3k2.00
[PDF]The Exact Time-Uniform Rate Frontier for Stochastic Gradient Descent on Smooth Convex Objectives▼4.5k2.67
[PDF]Multi-Round SPEAR++: Exact Data Reconstruction from Model Updates across communication rounds in Federated Learning▼4.3k2.00
[PDF]ECLIPSE: Orthogonal Subspace Projection for Triggerless Bias Injection in Diffusion Models▼1.2k1.67
[PDF]Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning▲3.0k2.33
[PDF]Static Gradient Attribution Underperforms a Density-Matched Random Mask Within LoRA’s B-Matrix▼1.2k1.67
[PDF]Implicit Low-Rank Training Dynamics in Directly Parameterized Lipschitz-Bounded deep Networks▲5103.00
[PDF]OrthVMS: Orthogonal Variational Multiscale Correction for Full-Rank Updates with Low-Rank Optimizer States▲3.9k1.67
[PDF]ABrA-GD: Adaptive Bregman Accelerated Gradient Descent for Relatively Smooth and (Strongly-)Convex Optimization▼4.3k2.00
[PDF]Optimal local linear convergence of Nesterov’s accelerated gradient method for functions under the Polyak–Łojasiewicz inequality▲3.0k2.33
[PDF]Understanding Forgetting Dynamics in Full Fine-Tuning of LLMs: A Neural Tangent Kernel Perspective▲3952.67
[PDF]When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation▲3.0k2.33
[PDF]Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning▲3.0k2.50
[PDF]Understanding and Mitigating Forgetting in LLM Full Fine-Tuning at the Parameter Level▼4.3k2.00
Withdrawn or desk rejected (106)
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00
[PDF]Beyond Training Loss: Full-Space Certificates for Neural JKO and Wasserstein EvolutionDesk rejected
[PDF]Certified Frozen-Midpoint Neural Integrators: Original-Energy Dissipation and Second-Order Physical TimeDesk rejected1.33
[PDF]Certified Quotient Natural Gradients in Wasserstein Space: Retractions, Ravines, and Higher-Order CollisionsDesk rejected