acceptodds: the papers of ICLR 2027
Abstract
The safe for work edition of acceptodds: the submissions, without the markets. Search them, browse them on a map laid out by what they are about, follow the ones you care about, keep reading lists with your group, and get recommendations from what you read. There are no odds, no bets and no reputation here. acceptodds is not affiliated with any organisation or institution. acceptodds is an open source project, open to contributions, at github.com/PotentialHedge/acceptodds-sfw.1 Follow for updates on X.
[PDF]KoopCell: Koopman-Based Generative Model for Learning Single-Cell Dynamics from Distribution Snapshots▲2603.67
[PDF]Learning While Scheduling Jobs under Context-Dependent Service Rates: An Anytime Rate-Optimal Algorithm▼363.67
[PDF]On Gradient Descent with Stochastic Rounding on Fixed-Point Grids for Quadratic Objectives▲1.9k3.67
[PDF]ConstraintGS: Modeling Primitive-Level Reconstruction Constraints for Sparse-View Gaussian Splatting▲2603.67
[PDF]Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation▲2603.67
[PDF]Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence▼363.67
[PDF]Piecewise Few-Spikes Neurons: Nonlinear Function Approximation for Provable and Efficient ANN-to-SNN Conversion3.67
[PDF]Mapping and Matching Joint Learning for Unpaired Unsupervised Visible-Infrared Person Re-Identification▲2603.67
[PDF]Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning3.67
[PDF]Learning What the Group Cannot Tell: Decomposed Critics for LLM Reinforcement Learning▲1.9k3.67
[PDF]VegBench: Quantifying the Ecological Resolution of Geospatial Models with Expert Field Surveys3.67
[PDF]Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing▲1.9k3.67
1 If this project is interesting to you, reach out at [email protected].