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]The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models▼2373.33
[PDF]Hidden Equivalences in Sheaf Neural Networks: The Share Credited to Matrix-Valued Transport Is Not Intrinsic▲1.7k3.33
[PDF]RGSM-GP: Reliability-Guided Semantic Memory for Iterative Graph Purification under Structural Attacks▲233.33
[PDF]Learning from Failures: Verified Edit Distillation for Variable-Length Diffusion Language Models▲1.7k3.33
[PDF]From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets▲6.5k3.33
[PDF]DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning▲233.33
[PDF]Commanding Humanoid by Free-form Language: A Large Language-Action Model with Unified Motion Vocabulary▲1.7k3.33
[PDF]Rewire then Express: Cascaded Flow Matching for Single-Cell Perturbation Response Prediction▲1.7k3.33
[PDF]Fine-tuning Disrupts Edit Readout: A Mechanistic Perspective on Model Editing Robustness▲233.33
[PDF]Uniform Discrete Diffusion Models Are Minimax Optimal for Estimating Distributions with Small Effective Support Size▲1.7k3.33
[PDF]The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark▲233.33
1 If this project is interesting to you, reach out at [email protected].