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]Counterfactual Twins and Executable Validity Gates for Diagnosing Spatial Reasoning in Multimodal LLMs▲31.00
[PDF]ALERT: Agents for Language-Guided Execution of Revocable Tasks in Real-Time Strategy Games▲31.00
[PDF]From-Base RLVR for Verify-Only Judges: A Rule-Based Reward Turns Base Models into Trajectory Auditors▲31.00
[PDF]From Experience to Deliberation: An Adaptive Cognitive Harness for LLM in Long-Term Traffic Simulation▲31.00
[PDF]Calibrated Pessimism in Offline Reinforcement Learning: Auditing Support-Conditioned Reliability and Control Transfer▲31.00
[PDF]Selection Is Not Evaluation: Maximization Bias in Scoring Runtime Interventions for Language Agents▲31.00
[PDF]Beyond Single Positives: An Empirical Audit of Solution-Set Adaptation for Code Retrieval▲31.00
[PDF]When to Search, Continue, or Fall Back: Risk-Controlled Routing for Rare-Regime Discovery▲31.00
[PDF]RICK: Certifying Transmission in Multi-Agent Credit Assignment via Worst-Regime Selection▲31.00
[PDF]Must Decision Making Be Trajectory-Centered? Behavioral Structure as a Relation-Centered Alternative▲31.00
[PDF]Hierarchical Reflective Policy Optimization for LongHorizon Agentic Reinforcement Learning▲31.00
[PDF]What the Nonnegative Lens Misses: Energy-Matched Causal Tests of the J-Space in Open Language Models▲31.00
[PDF]The Fate of a Failed Training Run: Recovery Dynamics and Replay-Buffer Pathology in Soft Actor-Critic▲31.00
[PDF]DFA-VLA: Dynamic Fine-Grained Alignment for Vision-Language-Action Models in Robotic Manipulation▲31.00
[PDF]The Half-Life of Repairs: Why Fixes Fail under Continued Training and How to Make Them Last▲31.00
[PDF]Distributed Geographic Identity Encoding in Vision-Language Models: From Linear Probing to Sparse Autoencoder Feature Ablation, and Why Post-Hoc Debiasing Fails▲31.00
[PDF]Beyond Multimodal Alignment: Shared Physical Representations Across Sensors and Action Orders▲31.00
[PDF]LoRA-Ring: Locality-Preserving Consistent Hashing for Dynamic Adapter Routing in Large Language Models▲31.00
[PDF]Federated Fine-Tuning of Code Language Models: A Comparison of FedAvg, FedProx, and FedAdam UnderLanguage-Heterogeneous Clients▲31.00
[PDF]Stacked Multimodal Fusion of Genetic and Histopathology Features for Survival Prediction in Breast Cancer▲31.00
[PDF]TopoMontage: Topology-Preserved Cross-Montage Alignment for Universal EEG Representation Learning▲31.00
1 If this project is interesting to you, reach out at [email protected].