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]GMNO on MaxwellBench: Scaling Pretrained General Mesh Neural Operator Across Industrial-Standard Electromagnetism Simulations▲233.33
[PDF]Stabilizing Independent Learning in General-Sum Self-Play via Coupling-Adaptive Regularization▲233.33
[PDF]DVGT-World: Extending Vision-Geometry Action Paradigms To 3D World Models For Autonomous Driving▲6.5k3.33
[PDF]Dynamic Clustering and Label Weighting for Unsupervised Aerial-Ground Person Re-Identification▲1.7k3.33
[PDF]RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution▲233.33
[PDF]Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation▲6.5k3.33
[PDF]Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction▲16k3.33
[PDF]GRADE: Evidence-Aligned Adaptive Granularity for Structure-Aware Residual Diffusion in Incomplete Multi-View Clustering▲6.5k3.33
[PDF]TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations▲233.33
[PDF]LAM++: Enhanced LocateAnything via High-Resolution Post-Training and Geometry-Aware Speculative Decoding▲1.7k3.33
[PDF]Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems▲6.5k3.33
[PDF]Sparse Activation Attributes for Frame Curation and Curriculum Scheduling in Imitation Learning▲6.5k3.33
[PDF]Score Addition Is Not Composition: Closed-Form Path Corrections for Training-Free Composition of Pretrained Flows▲1.7k3.33
1 If this project is interesting to you, reach out at [email protected].