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583 results for “keyword:"gradient"” in ICLR 2027. 106 withdrawn or desk rejected listed apart.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]Applied but Not Received: Designing Effective Surrogate Gradients for Spiking Neural Networks▼4.5k2.67
[PDF]Dimension Is Free, Horizon Is Not: When Evolution Strategies Rival Policy Gradients for LLM Fine-Tuning▼4.5k2.67
[PDF]Stochastic Subgradient Descent at Sharply Repulsive Points: A Bounded Noise Counterexample and Gaussian Noise Avoidance▲5103.00
[PDF]How Many, Not Which: Automatic Data Budgets for Conditional GANs Using Gradient Spectra▼1.2k1.67
[PDF]Two-Stage Prompt Optimization: From Reasoning-Guided Search to Gradient-Guided Refinement▼1.2k1.67
[PDF]Logarithmic Activation Clocks in Diagonal Linear Networks: When SGD Does and Does Not Follow Lasso▼1361.33
[PDF]Learning to Switch with Stability and Convergence Guarantees: Policy Gradient for State-Independent Controller Switching in Linear Systems▼1361.33
[PDF]Rotation-Based Gradient Balancing: Reconciling Alignment and Fidelity in Multi-Task Learning▼1.2k3.00
[PDF]Alignment Strength Is Not Enough: Backward Influence Allocation in Heterogeneous Multimodal Learning▲9.2k2.67
[PDF]Gradient Subspace Dynamics During Supervised Fine-Tuning of LLMs: Input–Output Asymmetry▼4.3k2.00
[PDF]ConCam: Anchor Consensus and Camouflaged Injection for Backdoor Attacks in Vertical Federated Learning▼1.2k1.67
[PDF]Convex-SKM-Net: Low-Latency Block Halfspace Corrections for Neural Convex Constraint Satisfaction▼4.3k2.00
[PDF]What Stochastic Information Matters for Learning? Observable-Relative Equivalence and Control▲3.0k2.33
[PDF]On Gradient Descent with Stochastic Rounding on Fixed-Point Grids for Quadratic Objectives▲1.9k3.67
[PDF]Resolvable-Effect Accounting for Tool-Calling Agents: Reward Bias and Evaluation Resolution▲11.00
Withdrawn or desk rejected (106)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