acceptodds: Which papers will get accepted at ICLR 2027?

Abstract

A prediction market on peer review. Each paper has a market on its decision (accept or reject), priced by researchers who stake $rep, an in app currency, on what they expect. Everyone who signs up receives 1,000 $rep to trade with. Prices are probabilities, and every market settles when the venue publishes its decisions. It is a game made for fun, and has no connection to ICLR, OpenReview or any other organisation. acceptodds is an open source project, open to contributions, at github.com/benedict-armstrong/acceptodds.¹

ICLR 2027sort:acceptance volume activity newest

[PDF]Orchestration within LLMs via Discovering and Orchestrating Internal Operators

[PDF]Residual-Augmented Latent Flow Matching for Graph Anomaly Detection

[PDF]Binary Expansion Group Intersection Network

[PDF]Molecular Conformer Sampling Beyond Generations

[PDF]PriGo: Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation

[PDF]TangramPuzzle: Benchmarking Geometric Constraint-Based Compositional Spatial Reasoning in MLLMs

[PDF]Multimodal Co-Generation with Continuous Bitstream Diffusion

[PDF]Compress to Improve: Reclaiming Output Budget from On-Policy Distillation for Stronger Reasoning

[PDF]From Perception to Integration: Revisiting the Internal Dynamics of Reasoning in Vision-Language Models

[PDF]Answer2Path: Outcome-Guided Acquisition of Reusable Web-Agent Experience

[PDF]Learning What and When to Transfer for Cross-Scene Hyperspectral Clustering

[PDF]CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

[PDF]Break the Chain, Gain a Margin: A Theory of Multi-Step Reasoning in LLMs

[PDF]Sparse Neural SIV: Learning Nonlinear Causal Relationships with Synthetic Instruments

[PDF]Privacy-Aware Dirichlet Process Mixture Models: Diffusion-Based Trajectory Protection and Differentially Private Weights

[PDF]From Triggers to Antigens: An Immune-Inspired Framework for Continual Backdoor Defense

[PDF]Prof-K: Probabilistic One-Pass Filtering for Efficient Top-

k

[PDF]Learning from the Near Future: Temporal Self-Distillation for RLVR

[PDF]REx: Small Language Model Agents with Recursive Execution and Subtree Compression

[PDF]MosaicDrive: Task-Aware Multi-Camera Reasoning for Autonomous Driving

[PDF]Nerve Faithfulness Certifies Data Geometry in Learned Dictionaries

[PDF]PolyWorld: Benchmarking Multimodal Reasoning over Evolving Polymers

[PDF]Gated Target Propagation for Compositional Generalization in Continual Learning

[PDF]Latency and Accuracy Tradeoffs in Spiking Neural Networks

[PDF]The Model Already Has a Dictionary: Cumulative SVD Features as a Training-Free Alternative to Sparse Autoencoders

[PDF]N×N E-VALUATION: Hypothesis Certification Without Per-Hypothesis Conditional Resampling Models

[PDF]SpecCert: Deterministic Joint Certification and Margin-Explicit Training for Graph Neural Networks

[PDF]AMBER: Training Long-Horizon Web Agents through Append-Only Memory

[PDF]DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies

[PDF]On Probability Misallocation in Single-Cell Perturbation Prediction

[PDF]Improved Convergence and Generalization Analysis for Online Knowledge Distillation

[PDF]Site-Aware Receptor-Sequence-Conditioned Peptide Binder Generation

[PDF]Breaking the Martingale Curse: Multi-Agent Debate via Epistemic Asymmetry

[PDF]The Entropy Bias of Hybrid Attention: Training Models to Be Sparse-Ready

[PDF]Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weakly Communicating

[PDF]LVMH: A Meta-Optimization Harness for Long-Video Agent Memory

[PDF]SemanticBN: From Individual Brain Networks To Evidence-Grounded Semantic Units

[PDF]When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning

[PDF]3D Primitive Assembly from Generative Anchors

[PDF]Preference-Aware Rubric Learning for Personalized Evaluation

[PDF]FORTA: Feedback-Guided Predictive Distribution Repair under Heterogeneous Shift

[PDF]ECHOROUTER: Forecast-Guided Evolution of Runtime-Adaptive Multi-Agent Systems

[PDF]Mixture-of-Kittens: MoE Megakernel for NVL72s

[PDF]Correct then Forecast: Observer State-Space Models for Time Series Forecasting

[PDF]SENTRY-BD: Bilevel Measurement Design for Cross-Context Perturbation Recovery

[PDF]Change2Act: Object-Centric Visual Reasoning for Image-Goal Manipulation

[PDF]EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

[PDF]Masked Self-Distillation: Internalizing the Chain-of-Thought in Language Models

[PDF]VADP-VLA: View-Adaptive Dynamic Visual Token Pruning for Efficient VLA Inference

[PDF]Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

¹ If this project is interesting to you, reach out at [email protected].