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]Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes▲1.7k3.33
[PDF]When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain▲1.7k3.33
[PDF]Don't Call It Privacy Until You Pick a Metric: Joint Auditing of Fine-Tuning and Privacy Metrics in Clinical LLMs▲1.7k3.33
[PDF]Beyond Person-Cue Suppression: Three-View Matched Contrastive Correction for Visual Cultural Attribution▲1.7k3.33
[PDF]Gaussian Stippling: Efficient Sorting-Free 3D Gaussian Rendering through Hybrid Sampling and Spatiotemporal Reconstruction▲233.33
[PDF]CoFlow: Stabilizing LLM Instruction Tuning via Gradient Flow Compatible Data Selection▲6.5k3.33
[PDF]AgentVIF: Event-Aware Multi-Agent Adaptation to Dynamic Degradations in Visible–Infrared Video Fusion▲6.5k3.33
[PDF]CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces▲1.7k3.33
[PDF]Compact Spatiotemporal Representations via Summary Tokens for Human Intracranial Recordings▲1.7k3.33
[PDF]SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation▲6.5k3.33
[PDF]HAD²RL: Heterogeneous-Agent Dense Reinforcement Learning for Adversarial Failure Search of Detect-and-Avoid Systems▲1.7k3.33
1 If this project is interesting to you, reach out at [email protected].