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]Matryoshka attribution: Learning to attribute language model outputs to representations and weights▲2603.67
[PDF]OSFAL: Orthogonal Cross-Spectral Feature Alignment and Layer-Localized Cross-View Learning for Any-Scenario Person Re-Identification▼363.67
[PDF]Structure as State, Not Skip: Bridging Semantic Representation and Structural Detail for 3D Medical Image Segmentation3.67
[PDF]Asking the World: Generalist Physical Reasoning through Agentic World Modeling and Probing▲1.9k3.67
[PDF]The Blessing of Linear Non-Gaussian Models: Powerful Independent Subspace Inference for Latent-Variable Causal Discovery3.67
[PDF]Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks▲2603.67
[PDF]Consistent Algorithms for Dynamic Non-Monotone Submodular Maximization with Efficient Updates▲2603.67
[PDF]When Good Brain Predictors Make Bad Brain Controllers: A Regression Theory of Prediction–Control Dissociation3.67
[PDF]SpinningRL: Boosting RLVR Efficiency with Theoretical Reward Gain Modeling and Adaptive UCB Sampling▲1.9k3.67
[PDF]Diagnosing Pixel-Space Diffusion Transformers: From Depth-Wise Connectivity to Layer-Wise Attention Patterns▲1.9k3.67
[PDF]Prior-Amortized In-Context Bayesian Inference for Generalized Linear Mixed-Effects Models▲1.9k3.67
[PDF]LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management▲2603.67
[PDF]DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents3.67
[PDF]Learn in Space: On-Policy Distillation via Spatial Divergence for Vision-Centric Reasoning▲1.9k3.67
[PDF]Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning▲6.7k3.67
1 If this project is interesting to you, reach out at [email protected].