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]How Much to Trust the Eyes? Reliability-Guided Inference for Diffusion-Based Audio-Visual Speech Enhancement▲4603.00
[PDF]A Computationally Efficient and Rate-optimal Algorithm for Adversarial Linear MDPs with (Aggregate) Bandit Feedback▲4603.00
[PDF]FalOTS: Orthogonal Target-Aware SAM for Federated Active Learning Under Global Class Imbalance▲4603.00
[PDF]SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-commerce Agents▲5.3k3.00
[PDF]The Calibration Set Is in the Checkpoint: How Release Geometry Governs Membership Leakage in Post-Training Quantization▼1.2k3.00
[PDF]Which Predictions Suffice for a World-Model Planner's Decision? Certifying Reward and Value Evidence by Re-Planning▲5.3k3.00
[PDF]Faster Last-Iterate Convergence for Zero-Sum Games with Stochastic Feedback via Anchor-Regularized Learning▼1.2k3.00
[PDF]How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits▲4603.00
[PDF]MixRoute: Mixed Parameterization with Adaptive Information Routing for Time Series Forecasting with Exogenous Variables▼1.2k3.00
[PDF]OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery▲4603.00
[PDF]Every Gene Count Has a Platform and a Slide: Measurement-Aware Observation Model for H&E-to-Spatial-Transcriptomics Prediction▼1.2k3.00
[PDF]OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools▲4603.00
1 If this project is interesting to you, reach out at [email protected].