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]EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA▼1371.33
[PDF]Compositional Context Encoding for Out-of-Distribution Generalization in Modular World Models▼1371.33
[PDF]Listen First, Look as Needed: Uncertainty-Aware Asymmetric Routing for Audio-Visual Recognition▼1371.33
[PDF]Autonomous Federated Learning: Incentive-Aligned, Energy-Aware, and Byzantine-Resilient Coordination▼1371.33
[PDF]Where Does Attention Mass Live? A Matched-Budget Study of Query-Adaptive Attention Sparsification for Decoder LMs▼1371.33
[PDF]Modality-Agnostic Anomaly Detection with Deterministic, Decomposable Uncertainty Quantification▼1371.33
[PDF]Do Language and Visual Perturbations Compound? Interaction Effects and Backend Sensitivity in Compact Vision-Language-Action Model Evaluation▼1371.33
[PDF]From AI Forecast to Text Report: Pangu-Driven Weather Report Generation via Vision-Language Fine-tuning▼1371.33
[PDF]Q-LEAP: Quantum-Inspired Localized Evolution and Anchor Projection for Cross-Subject sEMG Recognition▼1371.33
[PDF]HADBN: Learnable Hierarchical Aggregated Dynamic Brain Networks for Interpretable Brain Disorder Diagnosis▼1371.33
[PDF]Same Trajectories, Different Credit: Scoring-Rule Dependence in Tool-Fault Recovery Evaluation▼1371.33
[PDF]A Risk-Bounded Gate for Self-Improving Agents: Selecting Modifications as a Mean–Variance Knapsack▼1371.33
[PDF]DEEPSEARCHDAG: A DAG-STRUCTURED BENCHMARK FOR NODE-LEVEL EVALUATION OF DEEP SEARCH AGENTS▼1371.33
[PDF]DPR: From High-Entropy Tokens to Learning Claims — Matched Evaluation for Token-Selective LLM Reinforcement Learning▼1371.33
[PDF]Bridging Efficiency and Morality: Ethical LTL Construction for Faster Convergence in Q-Learning‘s Ethical Dilemmas▼1371.33
[PDF]Branch-JEPA: Learning Dynamics-Aware State Representations through Dual-Branch Patch Routing▼1371.33
[PDF]Surpassing VLA Performance: Online RL Training of Lightweight Policies with Minimal Human Interventions▼1371.33
[PDF]ActWeave: Efficient Action Generation for Vision-Language-Action Models via Hierarchical Autoregression and Wavefront Decoding▼1371.33
[PDF]From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement▼1371.33
1 If this project is interesting to you, reach out at [email protected].