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]Web2LongTraj: Scaling Long-Horizon Agent Trajectories from Natural Web Corpora for Mid-Training▼2153.50
[PDF]fDAG-ACDC: Uncertainty-Adaptive Factor-Count Selection for High-Dimensional Causal Discovery▲1.5k3.50
[PDF]LazyFlash: Forward-Dense, Backward-Sparse Attention for Accelerated Long-Context Fine-Tuning▲5.9k3.50
[PDF]Theta sweeps accelerate cognitive map learning by broadcasting information to unvisited regions▲1.5k3.50
[PDF]Graph-Discovering for Networked Restless Multi-Armed Bandits with Nonlinear Delayed Propagation▲503.50
[PDF]Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks▲16k3.50
[PDF]Prior-Corrected Anchor Learning with Direct Discrete Partitioning for Multi-View Clustering▲233.33
[PDF]Low-Rank Smooth Unified Anchor Tensor Nonnegative Orthogonal Factorization for Multi-view Clustering▲233.33
[PDF]Effects of Pretraining Concept Frequency and Semantic Similarity among Classes on CLIP Generalized Zero-Shot Accuracy▲233.33
[PDF]GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling▼2373.33
[PDF]Diversity with Axiomatic Guarantees in Polynomial Time: Resolving an Open Problem on Diversity Measures▲233.33
[PDF]ScaledGD for Underparameterized Matrix Factorization: Global Convergence and Stepsize Universality▲233.33
[PDF]Coupling Error Exploration for Incomplete Multi-View Missing Multi-Label Classification▼2373.33
1 If this project is interesting to you, reach out at [email protected].