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
2,482 results for “keyword:"sta"” in ICLR 2027. 730 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MARD: Multi-level Adaptive Representation Distillation across Heterogeneous Architectures for Egocentric Action Recognition▼4.3k2.00
[PDF]Representation–Propagation Learning for Closed-loop Error-Controlled Long-Horizon Aircraft Trajectory Forecasting▼4.3k2.00
[PDF]MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary▲422.75
[PDF]Semiparametric Efficiency for Entropic Optimal Transport under Structured Distribution Shift▼5.8k2.33
[PDF]AgentFrontier: Stabilizing Learning Frontiers in Reinforcement Learning for Active Reasoning Agents▲3.0k2.33
[PDF]Human Before the Loop: Constraining the Action Space Improves Security, Reliability, and Capability in AI Agents▼4.3k2.00
[PDF]Skeleton Keys: Estimating Randomized Model Selection Distributions With Limited Queries▼4.3k2.00
[PDF]Stability Does Not Mirror Plasticity: A Module-Level View of Declarative and Procedural Learning in Transformers▲3773.25
[PDF]Hybrid Reinforcement Learning under Dynamics Shift: Policy Optimization, Certification, and Adaptation▼4.3k2.00
[PDF]Self-Evolution Should Be Stable, Not Frozen: Lyapunov-Gated Recursive Self-Improvement▼4.3k2.00
[PDF]GAMPO: Auditing and Optimizing LSTM Memory for Partially Observable Reinforcement Learning▼4.3k2.00
[PDF]Testing Dependent Censoring via Mutual-Information Uncertainty and Deep Latent Imputation▲3.0k2.33
[PDF]Hidden Misalignment in Low-Field MRI Benchmark References: The Leaderboard Depends on How the Reference Is Built▼5.8k2.33
[PDF]Learning Where to Constrain: Meta-Learned Trust Allocation for Language-Model Reasoning▲20k2.67
Withdrawn or desk rejected (730)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]Beyond Local Cycles: Long-Horizon Repetitive Action Counting via Multi-Scale Temporal Representation LearningDesk rejected
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67
[PDF]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00