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]Nash Rejection Sampling: From Max–Min Games to On-Policy Optimization for Nash Learning from Human Feedback▲233.33
[PDF]CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Prediction▲1.7k3.33
[PDF]ARA: Asynchronous Restoration Attribution for Attention Heads in Diffusion Language Models▲1.7k3.33
[PDF]Broadcast, Reinforce, Repeat: Attention Dynamics Behind Repetition Collapse in Diffusion Language Model Forecasting▲1.7k3.33
[PDF]RoboPhyScan: A Large-Scale Sim-Ready Real-World Object Dataset with Manipulation Annotations▲6.5k3.33
[PDF]Nearly Linear Oracle Algorithms for Submodular Maximization under Matroid and Polymatroid Constraints▼2373.33
[PDF]Dense Weak Hiding: Closing Complexity Gaps in Nonconvex and PL Finite-Sum Optimization under Individual Smoothness▼2373.33
[PDF]Language as the Interface: Foundation-Model Contrastive Learning Links Transcriptomes and Electrophysiology▲16k3.33
[PDF]Efficient Inference for Distributional Treatment Effects with Partially Observed Outcomes▲26k3.33
[PDF]Broken Symmetry in BF16 Attention: Why FlashAttention Gradients Blow Up Late in Training▲233.33
[PDF]Task Conditions Tell More Than the Task: Dataset-Property Leakage and Private Release in World Action Models▲233.33
[PDF]Nice Fold or Hero Call: Learning Budget-Efficient Thinking under Policy-Dependent Solvability▲1.7k3.33
[PDF]Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones▲233.33
[PDF]On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction▼2373.33
[PDF]CoSplat: Complementary Surface Geometry Learning for Generalizable Surface Reconstruction▼2373.33
1 If this project is interesting to you, reach out at [email protected].