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]When Can Pairwise Routing Dynamics Be Tested in Mixture-of-Experts? Identifiability Conditions and Evidence from a Learned Router▼1371.33
[PDF]Replication Is Not Specificity: Negative Controls for Representation-Based Reward-Hacking Detection▼1371.33
[PDF]LLM Verifiers Are Wrong Together: Confident Consensus Errors Set the Floor for Failure Prediction▼1371.33
[PDF]Learning Latent Design Spaces for Efficient Optimization of Pixelated Electromagnetic Structures▼1371.33
[PDF]From Query to Knowledge Topology: Agentic Knowledge Extraction for Multi-Perspective Graph Retrieval▼1371.33
[PDF]Splatting Without Discrete Density Control: Lifted Gaussian-Mixture Kernel for CT Reconstruction▼5.3k1.33
[PDF]Constructive State Abstraction and Finite Identification in Autoregressive Transformers▼1371.33
[PDF]Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning▼1371.33
[PDF]Rethinking KL Regularization in RLHF: From Wrong Value Estimation to Correct Gradient Optimization▼1371.33
[PDF]Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration▼1371.33
[PDF]Beyond Relevance: Broad-to-Deep Contextual Evidence Reasoning for Retrieval-Augmented Medical Question Answering▼1371.33
[PDF]Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks▼5.3k1.33
[PDF]Transformers Miss the Middle Digits: Repairing Long Multiplication by Recursion and Robust Recombination▼1371.33
[PDF]What Should LLMs See, and How Often Should They Plan? World-State Encodings for Real-Time Games▼1371.33
[PDF]Visual Tokens Should Not Be Pruned Forever: Budgeted Visual Token Refresh for Multi-Turn LVLMs▼1371.33
[PDF]AutoFHE-Bench: Beyond Pass Rates in Agent-generated Fully Homomorphic Encryption Programs▼1371.33
[PDF]Does Probe Conditioning Isolate Composition? An Information-Control Audit of Multi-Hop Evaluation▼1371.33
[PDF]Diffusion Additive Models: Interpretable Generative Prediction through Feature-Wise Contributions▼1371.33
[PDF]Towards Autonomous Environmental Health: AERIS, a Research Agent for Air-Pollution Exposure Assessment▼1371.33
1 If this project is interesting to you, reach out at [email protected].