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
33,667 results for “keyword:"a"” in ICLR 2027. 8,396 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ScaledGD for Underparameterized Matrix Factorization: Global Convergence and Stepsize Universality▲573.50
[PDF]Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering▼4.3k2.00
[PDF]When Is Reweighting Not Enough? A Hodge Certificate for Rewiring Noisy and Incomplete Graphs▼5.9k2.33
[PDF]Demystifying Training-Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference▲9.2k2.67
[PDF]Query Complexity of Forward-Only Hebbian Learning: Theory and a Native Fit for Diffusion Models▼4.3k2.00
[PDF]Budgeted Multimodal Evidence Selection for Long-Video Understanding via Knapsack Optimization▲3.0k2.33
[PDF]IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback▼1.2k1.67
[PDF]From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model▲9.2k2.67
[PDF]Plottability Is Not Identifiability: Auditing the Retraining Stability of KAN Explanations▼1351.33
[PDF]Centered Kernel Distance: Dimension-Free Error Bounds for Comparing Neural Representations▼4.5k2.67
[PDF]Sample the Order, Not the Token: Test-Time Scaling for Masked Diffusion Language Models▲3762.67
[PDF]What Does a Training Token Buy? Contextual Information Gain Beyond Perplexity Across Open Model Suites▼1.2k1.67
[PDF]Learning the Maximum Tolerated Dose for Continuous Toxicity via Monotone Bayesian Trees▼1.2k1.67
[PDF]Measure First: The Noise Floor of an Autonomous Research Loop Dominates Its Accept Rule▼5.9k2.33
[PDF]SAFTER: Safety-Aware Filtered Training for Efficient and Robust Reinforcement Learning with Closed-Form Backup CBFs▼11k2.33
[PDF]The Calibration Set Is in the Checkpoint: How Release Geometry Governs Membership Leakage in Post-Training Quantization▼1.2k3.00
Withdrawn or desk rejected (8,396)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67