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]Alignment-Preserving Low-Dimensional Projection for Efficient Vision-Language Retrieval▼1371.33
[PDF]Freeze the Dynamics, Learn the Interface: Modular Recurrent Scaffolds for Compositional World Models▼1371.33
[PDF]ParadigmCoT: Paradigm-Guided Chain-of-Thought in Large Language Models via Policy Optimization▼1371.33
[PDF]ROEC: Record-Oriented Evidence Construction for Document-Level Structured Information Extraction▼1371.33
[PDF]Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance▼1371.33
[PDF]Statistical Certification of Neural Barrier Functions for invariance and Reach-Avoidance in Learning-Enabled Systems▼1371.33
[PDF]What Do Attack-Success Rates Measure? A Matched-Sham Control for GUI-Agent Injection Benchmarks▼1371.33
[PDF]Differential-Policy Double Deep Q-Network with Decoupled Architecture for Attitude Tracking of Quadrotor UAVs▼1371.33
[PDF]Mitigating Model Collapse in Latent Diffusion Models using a Lewis Signaling Regulariser▼1371.33
[PDF]Age Subspaces in 3D Face Representations: Readability, Predictive Dependence, and Transferability▼1371.33
[PDF]Green Quality Distance: Characterizing Energy and Quality Trade-Off in Open Text- to-Image and Text-to-Video Models▼1371.33
[PDF]Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression▼1371.33
[PDF]SPIRA: A Spatially-Variant Reinforcement-Learning Agent for Unsupervised Imaging Inverse Problems▼1371.33
[PDF]Compression Is Not Evaluation-Neutral: Fixed RAG Compression Can Distort Reader Comparisons▼1371.33
[PDF]BiGMNet: Bidirectional Representations with Predictive Supervision for EEG-Guided Target Speaker Extraction▼1371.33
[PDF]Adaptive Retrieval and Verification: A Shared Agentic Controller for Cybersecurity RAG and GraphRAG▼1371.33
[PDF]TimeGDC: Towards Efficient and Robust Joint Distribution Learning for Long-Term Probabilistic Time Series Forecasting▼1371.33
[PDF]Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models▼1371.33
1 If this project is interesting to you, reach out at [email protected].