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
2,416 results for “keyword:"training"” in ICLR 2027. 513 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Measuring Alignment Collapse: A Training-Free Framework for Object Hallucination in Vision-Language Models▼1361.33
[PDF]Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining▲6.1k2.00
[PDF]When Priors Veil the Threat: Backdoor Defense via Channel Activation Inspection for Pretrained Federated Learning▲3.0k2.33
[PDF]CCRT: A Single-State Optimizer with Retained Gradient History and Bounded Nonlinear Updates▼1361.33
[PDF]Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures▼4.5k2.67
[PDF]RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning▼1.2k1.67
[PDF]miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning▼4.5k2.67
[PDF]Denoising Strain: A Geometric Order Parameter That Reveals Learning Ahead of Eval Metrics▼1.3k1.75
[PDF]GEOEPS: TRAINING-FREE EVIDENCE PRESENTATION AND SELECTION FOR ULTRA-HIGH-RESOLUTION REMOTE SENSING UNDERSTANDING▼4.5k2.67
[PDF]Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post Training▼5.8k2.33
[PDF]The Geometry of Refusal: Why Post-Hoc Safety is Fragile and Pretraining-Time Safety Persists▼1.2k1.67
[PDF]Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?▼4.3k2.00
[PDF]RAMPing Up PINN Training Signals via Parameter-Sensitivity-Guided Collocation Refinement▲11k2.00
[PDF]Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach▼14k2.00
[PDF]On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators▲6.6k3.33
Withdrawn or desk rejected (513)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67