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]Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods▲1.7k3.33
[PDF]Distilling Reasoning Chain and Chain-Local Experiences for Few-Shot Multimodal In-Context Learning▲1.7k3.33
[PDF]K-JEPA: From Point to Distributional Prediction by Kernelized Joint-Embedding Predictive Architectures▲16k3.33
[PDF]Wired Together: Learning Persistent Relationships through Reward-Modulated Social Plasticity▲233.33
[PDF]Robust Multi-View Learning via Hybrid Geometric Reliability under Test-Time Noisy Correspondence▲233.33
[PDF]On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators▲6.5k3.33
[PDF]LLM-PowerTrace: A Dataset of Time-Resolved GPU Power Traces for LLM Fine-Tuning and Inference▲1.7k3.33
[PDF]Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL▲1.7k3.33
[PDF]Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation▲233.33
1 If this project is interesting to you, reach out at [email protected].