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2,416 results for “keyword:"training"” in ICLR 2027. 513 withdrawn or desk rejected listed apart.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]The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation▼4.5k2.67
[PDF]LazyFlash: Forward-Dense, Backward-Sparse Attention for Accelerated Long-Context Fine-Tuning▲4.7k3.25
[PDF]How Multi-Head Transformers Specialize for In-Context Learning: A Theoretical Analysis of Training Dynamics and Generalization▲2843.00
[PDF]Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning▲5103.00
[PDF]Robustness After Specialization: Installing Adversarial Robustness in Speech Foundation Model Descendants▲3952.67
[PDF]From Target Shift to Covariate Shift: How RL Post-Training Enables Transfer to New Tasks▼4.5k2.67
[PDF]HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents▲4.6k3.00
[PDF]Analysis of MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible error▲3952.67
[PDF]First-Order Characterization of Probabilistic Robustness for Classifiers via the Coarea Formula▲5103.00
[PDF]LSMXQ: Layerwise Salience-Aware Mixed-Precision Quantization for Efficient LLM Inference▼1361.33
[PDF]One Token Owns the Calibration Hessian: Why Layer-wise Quantization Can Silently Break Instruction Following▼1.2k3.00
[PDF]When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning▼1.2k1.67
[PDF]The Orthogonality Gap: Predicting, Before Training, When a Representation (or Foundation Model) Will Help▼1.2k1.67
[PDF]Does Distillation Leave a Trace? Source Detectability in Complex Post-Training Pipelines▲6.1k2.00
[PDF]Learning What to Check: Process Supervision with Artifact-Grounded Verification for Scientific Agents▼1361.33
[PDF]World-T : World-Test-Time Training as Persistent Memory for Real-Time Video World Models▼4.5k2.67
[PDF]One Self, Many Masks: Language Models Have a Self That Persists Beneath Their Personas▼1.2k1.67
Withdrawn or desk rejected (513)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