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
University of Illinois Urbana-Champaign
Birla Institute of Technology and Science, Pilani – Pilani Campus
Pohang University of Science and Technology
West Virginia University
Amazon
École Polytechnique Fédérale de Lausanne
Harvard University
Indian Institute of Technology Delhi
Los Alamos National Laboratory
Massachusetts Institute of Technology
Mila
Roche
Technical University of Munich
The Chinese University of Hong Kong
University of California, Irvine
University of Southern California
University of Tübingen
Aalto University
Delhi Technological University
ELLIS Institute Tübingen
Emory University
Indian Institute of Technology Kharagpur
Industrial University of Santander
INHA University
Ludwig-Maximilians-Universität München
New York University
Polytechnique Montréal
University of California, Los Angeles
University of California, Santa Barbara
University of Moratuwa
University of Pennsylvania
University of Surrey
Uppsala University
Virginia Tech
北京大学

ETH Zurich
University of Maryland, College Park
University of Illinois Urbana-Champaign
Birla Institute of Technology and Science, Pilani – Pilani Campus
Pohang University of Science and Technology
West Virginia University
Amazon
École Polytechnique Fédérale de Lausanne
Harvard University
Indian Institute of Technology Delhi
Los Alamos National Laboratory
Massachusetts Institute of Technology
Mila
Roche
Technical University of Munich
The Chinese University of Hong Kong
University of California, Irvine
University of Southern California
University of Tübingen
Aalto University
Delhi Technological University
ELLIS Institute Tübingen
Emory University
Indian Institute of Technology Kharagpur
Industrial University of Santander
INHA University
Ludwig-Maximilians-Universität München
New York University
Polytechnique Montréal
University of California, Los Angeles
University of California, Santa Barbara
University of Moratuwa
University of Pennsylvania
University of Surrey
Uppsala University
Virginia Tech
北京大学

ICLR 2027sort:activity acceptance volume newest

[PDF]DeMemSR: Transferable Degradation Representation Learning and Stable–Dynamic LR Memory Fusion for Diffusion-Based Real-World Image Super-Resolution

[PDF]HSI-Agent: Bridging Motion Dynamics and Scene Semantics for Unified Human-Scene Interaction Generation and Understanding

[PDF]Distribution-Calibrated Diffusion for One-Shot Federated Graph Classification

[PDF]HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation

[PDF]Z-WAM: Learning World-Action Models from Image-Editing Priors

[PDF]CXR-ContraBench: Auditing Polarity Reversals Beyond Aggregate Accuracy

[PDF]Uncertainty-Guided Adaptive Expert Selection for Graph Neural Networks

[PDF]The World Does Not Pause: Real-Time Benchmarks and Training-Free Acceleration for Dynamic Manipulation

[PDF]TIMBRE: Reliability-Aware Harmonic Consensus for Label-Free Multimodal Test-Time Reinforcement Learning

[PDF]Inter-Joint Relations Matter: Asymmetric Motion–Distance Denoising for Text-to-Motion Generation

[PDF]Stronger, Yet Not Better: Demystifying Self-Distillation Initialization

[PDF]Process Reward Informed Tree Rollout for Effective Multi-Turn RL

[PDF]INTERPRETABLE IMAGE RESTORATION VIA MINIMUM DESCRIPTION LENGTH ROUTING

[PDF]Learning Navigation Corrections from a Weak Recovery Policy

[PDF]LoadCalib: Cognitive-Load-Calibrated Chain-of-Thought Synthesis for Small Language Models

[PDF]FA-MoE: Fisher-Adaptive Routing for Sparse Vision-Language Mixture-of-Experts

[PDF]Rethinking Safety Reward Models in Long-Context Settings: Systematic Evaluation and Reliable Contextual Modeling

[PDF]Values Shape What Self-Improving Coding Agents Build

[PDF]LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation

[PDF]The Doctor’s Casebook: When LLMs Reason by Patient Analogy via Information Gain–Guided Graph Search

[PDF]h+1 heads express more than h heads

[PDF]A Dataset Is Worth Decomposing into Multiple Latent Domains: Reframing and Mitigating Base–New Trade-Off in Prompt Learning

[PDF]SubjectSwitch: Background-Preserving Subject Switching in Interactive Long Video Generation

[PDF]CANDLE: Cortical Null-Space Decomposition for Noninvasive Brain Source Imaging

[PDF]TraceEdit: Self-Evolving Multi-Channel Environment Attacks on GUI Agents

[PDF]MoRSE: Distilling EEG Foundation Models into a Single Montage-Robust Multi-Task Encoder

[PDF]EmoForecaster: Advancing Multimodal Emotion Forecasting via State-Transition Modeling and Evidence-Grounded Reasoning

[PDF]MSP-GNN: Learning First-Stage Decisions in Multistage Stochastic Programming via Subtree Permutation Invariance

[PDF]Learning What Is Worth Training: The Data-Value Bottleneck in LLM Self-Improvement

[PDF]Rethinking Layer Selection for Low-Rank Adaptation

[PDF]Scaling Multivariate Time Series Forecasting with Context-Modulated Prototype Attention

[PDF]When Small Evaluator Biases Become Permanent: Phase Transitions in Self-Evolving Agent Skill Libraries

[PDF]Align Before Distilling: Teacher-Aligned Repair for Compact One-Step Diffusion Models

[PDF]EVA: Efficient Training for Joint Video-Audio Generation via Selective Cross-Modal Interaction

[PDF]Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery

[PDF]Transport-Aware Inference on Vector Bundles: When Is Parallel Transport Statistically Beneficial?

[PDF]Scaling Laws For Attention-To-Recurrence Distillation

[PDF]Attend as You Act: Progress-Guided Adaptive Contextualization for Vision-Language-Action Models

[PDF]TokAudit: Auditing What Extra Capacity Buys in Time-Series Tokenizers

[PDF]Before You Ask: Learning to Proactively Initiate Interaction in Streaming Video

[PDF]FinerSR: Restoring Small but Semantically Critical Regions in Generative Video Super-Resolution

[PDF]ConTraPosE: Geometry-Aware Contrast Maximization for Event-Based Object Tracking

[PDF]Intervention-Dependent Selection Credit in Stateful Test-Time Adaptation

[PDF]Uncovering Latent Reasoning from Action Trajectories for Long-Horizon Agents

[PDF]Where Does RLVR Act? A Conserved Token Ledger for What Post-Training Adds to a Base Model

[PDF]Task-guided Cross-subgraph Topology Learning for Federated Graph Clustering

[PDF]The Price of Reliable Rotary Retrieval: Task Geometry, Shared Spectra, and Minimal Adaptation

[PDF]Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry

[PDF]QVRMem: Query-Time Validation and Reanswering for Evolving Memory

[PDF]How Does Pre-Trained Face Familiarity Affect the Decodability of Identity-Specific EEG Representations?

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