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]Preference Alignment Helps Probabilistic Forecasts Only When the Decision-Maker Cannot Adapt▼1371.33
[PDF]Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning▼1371.33
[PDF]Learn the Shape, Calibrate the Scale: Simulator-Trained Conformal Prediction under Sim-to-Real Shift▼1371.33
[PDF]AsymGAD: Label-Free Lateral-Movement Pivot Ranking via Asymmetric Graph Anomaly Detection▼1371.33
[PDF]When Better Classifiers Make Worse Tuners: IonTrapBench and History-Gated Stopping for Closed-Loop Mass Spectrometer Tuning▼1371.33
[PDF]When an Evaluation Rule Writes Training Labels: Measuring Human-Reference Forgiveness in NAVSIM▼5.3k1.33
[PDF]How Much of Anomaly Segmentation Is Background? A Published 97% Pixel AUROC Can Certify Chance Inside the Object▼1371.33
[PDF]From Relevant Fragments to Sufficient Answers: Verifiable Evidence Chains in Long Dialogues▼1371.33
[PDF]SKILLGRAPH: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs▼1371.33
[PDF]Learning under Mechanism-Induced Covariate Shift: Finite-Scale Coverage and Source Allocation▼1371.33
[PDF]A Pre-Registered Invariance Audit of Post-Hoc Out-of-Distribution Detectors under Exact Network Symmetries▼1371.33
[PDF]**StatOrch: Evidence-Conditioned Stagewise Inference Under Unknown Distribution Shift**▼1371.33
[PDF]IMPACT: Measuring Conditional Workflow Responses to Single-Span Model Substitution in Stateful LLM Agents▼1371.33
[PDF]HiR-MKR: Hierarchical Reconstruction and Multi-Source Knowledge Retrieval for Semi-Structured Table Question Answering▼1371.33
[PDF]GROVE: Governed Rule Operationalization through Verifiable Agentic Evolution for Multimodal Moderation▼1371.33
[PDF]When Motion Logs Go Missing: Selective Visual Recovery for Persistent GUI State Tracking▼1371.33
[PDF]Safety Is Not Conserved: Constraining Self-Improvement Across Models and Agent Harnesses▼1371.33
[PDF]When Is Self-Repair No Longer Possible? Certifying Irrecoverable Turning Points in Tool-Using Agents▼1371.33
[PDF]PLAN AROUND CHANGES, LEARN FROM VIOLATIONS: PERSISTENT TASK STATE FOR LONG-HORIZON VLA AGENTS▼1371.33
[PDF]An Identifiability Hierarchy for Mechanistic Interpretability: Interpretability Claims Live at Different Levels of Identifiability▼1371.33
1 If this project is interesting to you, reach out at [email protected].