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]Fixed Rankings, Moving Leaders: A Relevance-Label and Source-Identity Audit of Scientific Retrieval Evaluation▼1371.33
[PDF]From Hidden States to Probability Measures: Measuring Quantization-Induced Deformation in Large Language Models▼1371.33
[PDF]Scaling Feedback Alone Is Not Scaling Supervision: From Prediction Quality to Decision Quality in Reward Learning▼1371.33
[PDF]Beyond the Current Observation: History-Informed Adaptation for Vision-Language-Action Models▼1371.33
[PDF]Beyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation Models▼1371.33
[PDF]From Forecast Error to Triage Decisions: Patient-Centered Evaluation of ICU Vital-Sign Forecasting▼1371.33
[PDF]A Falsification Study of Coupled-Constraint Telemetry Diagnostics in Multi-Agent Learning▼1371.33
[PDF]RTWorld: Benchmarking Real-Time Game Playing Agent for Open-Ended Tasks in Digital Environment▼1371.33
[PDF]When Recovery Creates Resistance: Instrumental Shutdown Avoidance from Gridworlds to Language-Model Agents▼5.3k1.33
[PDF]Perturbation Attribution Fragmentation under Alias-Redundant Evidence in Knowledge-Graph RAG▼1371.33
[PDF]Acting Is Easier Than Adapting: The Geometry and Design of Adaptation-Sufficient Representations▼1371.33
[PDF]BEYOND FIRST CROSSINGS: PRESERVATION IN FACTUAL REWRITING AT MATCHED MEAN OPTIMIZATION-PROMPT LOSS▼1371.33
[PDF]Does Better Estimation Imply Better Selection? A Decision-Theoretic Audit of LLM Agent Updates▼1371.33
[PDF]Share Poses, Not Pixels: An Interventional Study of Shared World Models for Multi-Agent Navigation▼5.3k1.33
[PDF]Dictionary Size and Dead Latents Handling Jointly Set the Recovery-Optimal Sparsity of Top-K Sparse Autoencoders▼1371.33
[PDF]Six Requirements for Inference-Time Self-Iterating Models: Representation, Uncertainty, and Local Credit▼1371.33
[PDF]When Can Expert Corrections Be Trusted? Evidence, Limits, and Risk-Controlled Decisions Across Environments▼1371.33
[PDF]How Much Evaluation Is Enough? Risk-Aware Adaptive Evaluation (RAAE) of LLMs in High-Stakes Financial Applications▼1371.33
[PDF]Not Which Path, but What Happens Before You Would Stop: What Reasoning Post-Training Changes▼1371.33
[PDF]A Plasticity Model of Cerebellar Regulation of Cortical Dynamical Stability and Task-Associated Representations▼1371.33
[PDF]Same Counts, Different Cost: Measuring the Order Gap in Sparse Mixture-of-Experts Routing▼1371.33
[PDF]CAVEAT: Two-View Auditing with a Deterministic Veto Lowers GUI-Agent Verifier False Positives Below Recorded LLM Judges▼1371.33
[PDF]Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs▼1371.33
[PDF]Errors and path-dependencies in LLM descriptions of the world: An analysis via maps and routes▼1371.33
[PDF]When Does Query-Aware Quantization Help? From Redundancy In-Distribution to Gains in Multimodal Retrieval▼1371.33
[PDF]Self-Consistent and Extremal Activation Functions: A Variational Theory of Activation Design▼1371.33
1 If this project is interesting to you, reach out at [email protected].