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

Join traders from

ETH Zurich
University of Maryland, College Park
Pohang University of Science and Technology
Birla Institute of Technology and Science, Pilani – Pilani Campus
Amazon
École Polytechnique Fédérale de Lausanne
Harvard University
Los Alamos National Laboratory
Mila
Roche
Technical University of Munich
University of Illinois Urbana-Champaign
University of Tübingen
Aalto University
Delhi Technological University
ELLIS Institute Tübingen
Indian Institute of Technology Delhi
Industrial University of Santander
INHA University
New York University
University of California, Irvine
University of California, Santa Barbara
University of Pennsylvania
University of Southern California
University of Surrey
Uppsala University
Virginia Tech
West Virginia University

ETH Zurich
University of Maryland, College Park
Pohang University of Science and Technology
Birla Institute of Technology and Science, Pilani – Pilani Campus
Amazon
École Polytechnique Fédérale de Lausanne
Harvard University
Los Alamos National Laboratory
Mila
Roche
Technical University of Munich
University of Illinois Urbana-Champaign
University of Tübingen
Aalto University
Delhi Technological University
ELLIS Institute Tübingen
Indian Institute of Technology Delhi
Industrial University of Santander
INHA University
New York University
University of California, Irvine
University of California, Santa Barbara
University of Pennsylvania
University of Southern California
University of Surrey
Uppsala University
Virginia Tech
West Virginia University

ICLR 2027sort:activity acceptance volume newest

[PDF]Sample Efficient GRPO via Learning to Reuse Tokens Across Trajectories

[PDF]RIVA: An Open Recipe for Agentic Full-Duplex Speech Models

[PDF]Flexible and Evolving Model Merging via Task Interference Modeling

[PDF]Towards Adaptive Temporal Credit Assignment via Bidirectional Fractional Operators

[PDF]Agentic Search for Counterfactual Recourse under Fixed LLM Budgets

[PDF]Freedom Causes Neural Generalisation

[PDF]VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

[PDF]ProoFit: Confidential Auditing of Model Overfitting

[PDF]HarnessWeaver: Continual Self-Improvement through Task-Conditioned Harness Composition and Model Routing

[PDF]Low-Regret Learning in Strategic Bandits via Incentive Design

[PDF]Probe and Calibrate: Stochastic Firing-Boundary Adaptation for Spiking Neural Networks

[PDF]REFUSALTRACE: Sparse Activation Masking for Jailbreaking via Natural Refusal Trajectories

[PDF]SCALE: Controlling Compositional Capability Gains in Black-Box LLMs

[PDF]Position, Not Content: What Repairs Question-First Prompting in Vision-Language Models

[PDF]Contrastive Image-Metadata Pre-Training for Materials Transmission Electron Microscopy

[PDF]LinMorph: Learning to Morph Softmax Weights for Efficient Video DiT Linearization

[PDF]Disentanglement from Nonlinear Task Sparsity

[PDF]SReg: Effectively Registering Point Clouds of Different Scales

[PDF]Mind the Curvature: Correcting Structural Bias in Bures–Wasserstein Regression

[PDF]AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos

[PDF]VLNAPO: Gradient-Guided Harness Engineering with Key-Token Supervision for Full-Game VLNA Policy Optimization in OpenRA

[PDF]A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

[PDF]Do Hierarchical Vision Backbones Need a Fourth Stage?

[PDF]LocusGate: Operator-Neutral Graph Workspaces for Composable Pangenome Queries

[PDF]Rethinking Routing Exploration in Modern Mixture-of-Experts

[PDF]Self-Play Pretraining with Zero-Data

[PDF]Learning to Act and Edit in Video Worlds

[PDF]WoCA: World Simulation with Compositional Assets

[PDF]A Ticket from Marginals to Joints: Coupled-Noise Distillation for One-Step Block Generation in Diffusion Language Models

[PDF]Replay-Conditioned Explanations: Disentangling Current, Historical, and Constraint Effects in Memory-Based Reinforcement Learning

[PDF]COMAS: Co-Optimizing Model and Policy in Stochastic Contextual Bandits

[PDF]Org-Agent: Beyond Personal Assistants Towards Organizational Agents

[PDF]RespFocus: Learning Temporal Evidence for Weakly Supervised Respiratory Sound Classification

[PDF]State-conditioned Pedagogical Adaptive Routing for Exercise Recommendation

[PDF]ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning

[PDF]PAIR: Prediction with Additive Intermediate Readouts for Long-Horizon PDE Forecasting

[PDF]Beyond In-Task Accuracy: Evaluating Task-Specialized Memory under Relevance Shifts

[PDF]More Correct Labels Can Hurt: Delayed Feedback in Streaming Activity Recognition

[PDF]How Far Can Sliding Window Attention See?

[PDF]Beyond Global Latents: Chunk-Based Sparse Grid VAE for Scalable 3D Modeling

[PDF]When Worlds Meet: Benchmarking Implicit Causal Reasoning with IRS-Bench

[PDF]Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

[PDF]Coverage-Gated Coalitional Coding for Multi-Modal Discrete Tokens

[PDF]JEPA LEARNS WHAT THE MASK LEAVES UNRECOVERABLE

[PDF]What Can Latent World Models Know? Physical Information in Multimodal Predictive Representations

[PDF]PCAF: Bounded Exact-Successor Memory for Efficient Language Models

[PDF]Localized Subspace Source Adaptation for Flow Matching

[PDF]Better Samples, Wrong Odds: When Prediction Rewards Distort World-Model Probabilities

[PDF]Complete the Scene, Cover the Video: Recurrent Token Compression for Video LLMs

[PDF]LEARNING FROM USER EDITS IN DICTATION SYSTEMS: ATTRIBUTION AND ADAPTATION

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