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
66 results for “keyword:"gradients"” in ICLR 2027. 10 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Does Local Credit Assignment Improve Shared Policy Gradients in Multi-Agent Reinforcement Learning?▼5.8k2.33
[PDF]Applied but Not Received: Designing Effective Surrogate Gradients for Spiking Neural Networks▼4.5k2.67
[PDF]What Stochastic Information Matters for Learning? Observable-Relative Equivalence and Control▲3.0k2.33
[PDF]An Empirical Evaluation Framework for Auditing Explainable AI in Network Intrusion Detection▲3.9k1.67
[PDF]EG-Opt: Efficient Learning for Nonlinear Programming via Explicit Gradients from Sample-Calibrated Linear Surrogates▼5.8k2.33
[PDF]Finite-Shot Quantum Federated Learning: Trajectory-Dependent Update Discrepancies and Nonconvex Convergence under Proximal Dynamics▼4.3k2.00
[PDF]AdvG: A Provably Convergent Actor–Critic Algorithm for Reinforcement Learning in Continuous Time and Space▲5103.00
[PDF]When Does Branching Pay? An Exact Variance Analysis of Tree-Structured Policy Gradients▼4.3k2.00
[PDF]Time and Cause: Reliability-Adaptive Hybrid Credit Assignment in Reinforcement Learning▲9.2k2.67
[PDF]Skipping Recomputation During Training: from Recurrent Models to Model Predictive Control and Beyond▼1611.50
[PDF]Sigmoid Contact Smoothing Recovers a Local Boundary Term in First-Order Pathwise Gradients▲3.0k2.33
[PDF]WHICH VERIFIER ERRORS REACH THE GRADIENT? A MOMENT DECOMPOSITION FOR AUDITING GROUP- RELATIVE REINFORCEMENT LEARNING▼5.8k2.33
[PDF]Diagnosing and Mitigating Sycophancy in LLMs via Attribution-Guided Activation Steering▼1.2k1.67
[PDF]How Reliable Is Online Training Through Time? A Convergence and Diagnostic Framework for Spiking Neural Networks▼5.8k2.33
[PDF]ACE-Guard: Automated Co-Evolutionary Guardrails for LLM Security via Inference-Time Natural Language Gradients▼1361.33
[PDF]Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback▲3972.67
[PDF]When Is a Policy-Gradient Batch Reliable? Identification Limits Under Severe Uncertainty▼5.8k2.33
Withdrawn or desk rejected (10)
[PDF]Same Objective, Different Optimizer: Preference-Flip Noise versus Label Smoothing in DPODesk rejected
[PDF]Dissecting Reinforcement Learning: Mechanisms Behind Compositional Reasoning in LLMsWithdrawn1.67
[PDF]Multiscale Regularization of Physics-Informed Neural Networks Based on a Maximal Local Oscillation Operator for Problems with Sharp GradientsWithdrawn1.00
[PDF]RHDP: A Gradient-Variation-Aware Reward Hacking Detection and Penalization Mechanism for Chest X-ray Report GenerationWithdrawn1.00