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]Different Bonuses, Similar Outcomes: Understanding Auxiliary Reward Non-Separation in PPO▼1371.33
[PDF]Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory▼1371.33
[PDF]Compositional Permission Flow Verification for Multi-Agent LLM Systems with Adaptive Security Consolidation▼1371.33
[PDF]Where Should Multimodal Test-Time Adaptation Capacity Live? A Controlled Study of Prompts and Residual Adapters▼1371.33
[PDF]CTDG-THOR: Query-Side Second-Order Temporal History Routing for Continuous-Time Dynamic Graphs▼1371.33
[PDF]Cross-Modal Patch Distillation with Budget-Enforced Any-Resolution Routing for Long-Context Compression▼1371.33
[PDF]Failure Migration in GUI Agents: Outcome Churn and the Trade-offs of Reflective Recovery▼1371.33
[PDF]MetaGround: Physics-Grounded Conditional Diffusion for Nonlinear Metamaterial Inverse Design▼1371.33
[PDF]Better Reconstruction, Worse Transfer: Probing Representation Geometry in Cross-Reynolds Generalisation▼1371.33
[PDF]Decay-Weighted Survivability Estimators: A Nonparametric Class of Regime Detectors with Bounded Forgetting and Reactivation▼1371.33
[PDF]Beyond Tool–Raw Comparisons: Matched-Control Attribution of Semantic Assistance for Code Reasoning▼1371.33
[PDF]Beyond the Population Prior: Reliable and Amortizable Person Representations in Models of Human Decision-Making▼1371.33
[PDF]Edit the Model You Deploy: Quantization Weakens Knowledge Edits Through Their Conditioning▼1371.33
[PDF]RACE: RELATION-LEVEL COUNTERFACTUAL EXPLANATIONS FOR HETEROGENEOUS GRAPH NEURAL NETWORKS▼1371.33
[PDF]HEIR: When the Student Inherits the Teacher's Seat Pareto-Competitive Reference Selection for On-Policy Self-Distillation of Reasoning LLMs▼5.3k1.33
[PDF]Reweight, Do Not Re-calibrate: Reusing the Same Encoder-Predictor Pair (World Model) When the Policy or Query Changes▼1371.33
[PDF]Scoring the Same Outputs: How Answer-Extractor Choice and Consistency Change Benchmark Comparisons▼1371.33
[PDF]PulseSyn: Learning to Co-optimize Reversible Logic Synthesis and Quantum Control Pulses▼1371.33
[PDF]Protect Before Evicting: Lagrangian-Guided Encoder Caching for Disaggregated Multimodal LLM Serving▼1371.33
1 If this project is interesting to you, reach out at [email protected].