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
82 results for “keyword:"efficient training"” in ICLR 2027. 17 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Removing Redundant Computation in a BDH-GPU-Derived Language Model: Exact Recurrent Training and Conditional Neuron Selection▲11.00
[PDF]How Many, Not Which: Automatic Data Budgets for Conditional GANs Using Gradient Spectra▼1.2k1.67
[PDF]CoSelTune: Co-Designing Token Selection and Backward Computation for Efficient Long-Context Fine-Tuning▼4.3k2.00
[PDF]TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel▼1.2k3.00
[PDF]Query Complexity of Forward-Only Hebbian Learning: Theory and a Native Fit for Diffusion Models▼4.3k2.00
[PDF]GhostMatch: Validation-Free Online Batch Selection for LLM Training via Submodular Gradient Matching▼1.2k1.67
[PDF]ResQAdam: Residual-Preserving Adaptive Optimization for Memory-Efficient Quantization Aware Training▼4.5k2.67
[PDF]Teach the Way It Thinks: Guiding LLM Post-training Data Engineering with Sparse Autoencoders▼5.8k2.33
[PDF]No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability▼4.5k2.67
[PDF]RAGE: Reference-Guided Data Resampling via Adaptive Gradient Estimation for Time Series Foundation Models▲9.2k2.67
[PDF]CoFlow: Stabilizing LLM Instruction Tuning via Gradient Flow Compatible Data Selection▲6.6k3.33
[PDF]Attract to Align, Repel to Differentiate: Contrastive Representation Alignment for Diffusion Models▼5.8k2.33
Withdrawn or desk rejected (17)
[PDF]LACS: Distribution-Sensitive Label-Agnostic Confidence Selection for Dynamic Data PruningDesk rejected
[PDF]Restoring Inputs Is Not Restoring Learning: Sparse Restoration in Multimodal TrainingDesk rejected1.67
[PDF]Not All Tokens Are Equal: Importance-Aware Masking for Discrete Diffusion Language ModelsWithdrawn1.00
[PDF]Endogenous Signals Fail to Allocate: Per-Token Compute Value Is Real, Transient, and Not LearnableWithdrawn1.33