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]Beyond Uniform Soft Thinking: Adaptive Gating and Calibration of Soft Tokens for Latent Reasoning▲233.33
[PDF]Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamcis, Convergence Rates, and Benefits of Off-Policyness▲233.33
[PDF]Interpreting Multi-layer Transformers for In-context Linear Regression with Varying Covariance▲1.7k3.33
[PDF]LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention▲233.33
[PDF]Scaling Parameter and Context in Attention: Native Sparse Attention from Mixture-of-Head▲1.7k3.33
[PDF]Semantic-Guided Cross-View Latent Transport via Flow Matching for Incomplete Multi-View Clustering▲233.33
[PDF]Symmetric Composition of Anisotropic Operators for Global Subseasonal-to-Seasonal Climate Forecasting▲233.33
[PDF]A Latent Distribution Perspective on Evaluating and Improving Latent Generative Models▲6.5k3.33
[PDF]Constructed Negatives Shape the Evaluation of Sequence-Based Protein–Protein Interaction Models▲6.5k3.33
[PDF]Beyond View Heterogeneity: Federated Incomplete Multi-View Clustering with Arbitrary View Subsets▲233.33
[PDF]MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier Auditing▲1.7k3.33
1 If this project is interesting to you, reach out at [email protected].