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
1,219 results for “keyword:"spe"” in ICLR 2027. 253 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]One Marginal Is Enough: What Doubly Stochastic Routing Buys Hyper-Connections, and What It Costs▲3.0k2.33
[PDF]Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer▼1.2k3.00
[PDF]CurriculumWorldBench: Benchmarking Autonomous Reconstruction of Executable University Curricula from the Web▲3.0k2.33
[PDF]Give the Drafter a Second Chance to Guess: Parallel Reconsideration for Speculative Decoding▼4.5k2.67
[PDF]When Not to Trust a Global Gaussian Process Posterior: Local Scoring and Progressive Dissonance for Multi-Modal Scientific Discovery▼1.2k1.67
[PDF]Understanding Optimization from Activation and Gradient Spectra: A Modded-NanoGPT Study▼13k2.00
[PDF]Steer, Then Classify: Adaptive Document-specific Representation Steering for Text Classification▼1.2k1.67
[PDF]Adversarial Stability of Deep GCNs under Adam: Worst-Case Bounds and Residual-Path Diagnostics▲3.0k2.33
[PDF]SysRepair-Bench: Measuring Whether Agents Can Fix a Vulnerability Without Breaking the Service▼4.5k2.67
[PDF]Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series▲19k2.33
[PDF]Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs▼4.3k2.00
[PDF]Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs▼4.3k2.00
[PDF]BIMArena: Benchmarking Domain-Specialized Computer-Use in Professional Building Modeling▲5103.00
[PDF]How Far Can Synthetic Speech Take Us? Synthetic Data Recipes for Pretraining Multilingual Speech Language Models▼4.3k2.00
[PDF]The Comparison Graph Determines What RLHF Can Learn: Spectral Identifiability, Error Bounds, and a Pre-Training Diagnostic for Preference Data▲3.0k2.33
Withdrawn or desk rejected (253)
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33