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]BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding▼1.2k3.00
[PDF]Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding▲5.3k3.00
[PDF]LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling▲4603.00
[PDF]Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning▲5.3k3.00
[PDF]Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure▲4603.00
[PDF]Optimal Recursive Composition and Dyadic Phase Laws for Gradient Descent with Predetermined Stepsizes▲4603.00
[PDF]GeoSlice-MGN: Analysis-Guided Geometric Routing for Impact Response Prediction in Realistic Structures▲5.3k3.00
[PDF]Count the Groups, Not the Configurations: Exact Inference and Learning at Fixed Totals▲4.7k3.00
[PDF]Better Trajectories, Not More: Paired Posterior Correction for Flow-Matching Inverse Problems▼1.2k3.00
1 If this project is interesting to you, reach out at [email protected].