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]LoadCalib: Cognitive-Load-Calibrated Chain-of-Thought Synthesis for Small Language Models▲31.00
[PDF]Two Asymmetries of LLM Self-Review: Family-Dependent Recall Gaps and Same-Model False-Positive Bias▲31.00
[PDF]Risk-Controlled Post-Compression Verification for Visual Token Reduction with Exact Dense Fallback▼2.0k1.00
[PDF]Selection Is Not Validation: Auditing Proxy-to-Behavior Reversals in Language-Model Data Curation▲31.00
[PDF]SD-LLaVA: Dual-Stream Vision-Language Reasoning with Structured Semantic Priors for BEV Understanding▲31.00
[PDF]LayerShield-QAT: Accuracy-Preserving Integer Quantization for Physics-Grounded Edge Regression▲31.00
[PDF]Wrong Rays: In-Distribution Accuracy Does Not Certify Transport in Learned PDE Propagators▲31.00
[PDF]Your VAE Knows Where to Sample, Not What It Doesn't Know: Merged Aggregated Posteriors as Deterministic Priors and Cluster Maps▲31.00
[PDF]Mechanova: An Autonomous Scientist for Discovering Falsifiable Mechanisms of Immune-Cold-to-Hot Conversion in Tumors▲31.00
[PDF]What Neighbors should an LLM See? A Systematic Empirical Study of Graph Neighborhood Serialization▲31.00
[PDF]Value-Twisted Sequential Monte Carlo for Task-Aware Missing-Modality Connectome Completion▲31.00
[PDF]Emergent, Coordinate-Specific Structure in Dense Parameter Updates for Continual Learning▲31.00
[PDF]How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models▲31.00
[PDF]From Model Coverage to Control Value: Auditing Few-Shot Safety Filters under Topology Shift▲31.00
[PDF]The Rate Measure: How Far Linearisation Governs Training, and Why That Horizon Cannot Be Read▲31.00
[PDF]When Learned Options Become Infrastructure: Promotion-Induced Maintenance in Control Lifecycles▲31.00
[PDF]The Prompt Effect: How Conditioning Strength Shapes Stereotype Differentiation in Text-to-Image Diffusion Models▲31.00
[PDF]Causal-Role Recurrence, Geometric Variation, and Objective-Conditioned Readout Across Mamba-1 Scales▲31.00
[PDF]Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories▲31.00
[PDF]Diagnosing Faults in Reinforcement Learning Simulators with Canonical Polynomial Invariants▲31.00
[PDF]Reasoning Geometry of Language Models: How Prompting, Training, and Scale Shape Judgment Trajectories▲31.00
1 If this project is interesting to you, reach out at [email protected].