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
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
West Virginia University
Aalto University
Delhi Technological University
ELLIS Institute Tübingen
Emory University
Indian Institute of Technology Kharagpur
Industrial University of Santander
INHA University
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

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
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
West Virginia University
Aalto University
Delhi Technological University
ELLIS Institute Tübingen
Emory University
Indian Institute of Technology Kharagpur
Industrial University of Santander
INHA University
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

ICLR 2027sort:activity acceptance volume newest

[PDF]MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning

[PDF]Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations

[PDF]NADA: Unlocking Fast and Accurate NVFP4 PTQ through Distortion-Aware Optimization

[PDF]Coarse Temporal Feedback for Test-Time Adaptation in Streaming Time-Series Anomaly Detection

[PDF]Stable Forgetting: Bounded Parameter-Efficient Unlearning in LLMs

[PDF]What Happens Inside VLAs for Compositional Generalization? A Mechanistic Analysis

[PDF]Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

[PDF]HIRE: Hippocampal Replay for Test-Time Agentic Reinforcement Learning

[PDF]Dormant in ANNs, Activated in SNNs: Stealthy Backdoor Attacks via ANN-to-SNN Conversion

[PDF]SkillLineage: Black-Box Provenance Auditing of Agent Skills Across Language Models

[PDF]Beyond Source Simulation: Pretraining with Proxy Governing Equations

[PDF]FedPOB: Sample-efficient Federated Prompt Optimization via Bandits

[PDF]DPLongSyn: Differentially Private Longitudinal Image Synthesis

[PDF]FaceKeeper: Multi-Expert LoRA for High-Fidelity Portrait Retouching

[PDF]Bayesian Intelligence from the Outside

[PDF]CABM: Efficient Concept Augmentation for Interpretable Deep Models

[PDF]Alignment Changes the Response Policy, Not the Affect Representation

[PDF]Reward-Guided Noise-Level Trajectories and Task-Aware Evaluation for Image Editing

[PDF]Hilbert Split: Geometry-Aware Data Splitting for Generalization Assessment

[PDF]M³DT-RL: Multimodal Multidisciplinary Diagnostic Teaming with Reinforcement Learning

[PDF]SimRec: Learning to Search, Ask, and Recommend from Simulated Interaction

[PDF]Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

[PDF]Weight-Space Learning Without Weights: Leveraging Neural Operators for Model Editing

[PDF]Address Migration for Replay-Free Continual Learning with Sparse Routed Memories

[PDF]INVARIANCE DOES NOT GUARANTEE REPAIR IN FROZEN-FEATURE DETECTORS

[PDF]GEEZ: Grounded, Efficient, and Effective Video Understanding

[PDF]Window-Level Differentially Private Fine-Tuning of Vision-Language-Action Models

[PDF]Locks and Keys: Learning Scientific Inspiration Retrieval as Pattern Matching at Scale

[PDF]When to Unpair: Regulating Pairing Dependence in Medical Visual In-Context Learning

[PDF]PrefGeo: Preference Geometry for Multi-Preference Fusion of Flow Matching Models

[PDF]Heard but Not Heeded: Language Survives in a VLA's Representations but Not Its Actions

[PDF]AUDITING TRAINING–EVALUATION OVERLAP, NEGATIVE SAMPLING, AND RERANKING IN MULTILINGUAL PATENT RETRIEVAL

[PDF]GeoState: Pretrained Geospatial Embeddings Are Forecastable Where the Land Changes

[PDF]Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants

[PDF]Advantage-Gated Anchoring for Diffusion Reinforcement Learning

[PDF]CoSR: Memory-Efficient FP8 Training for Multitask Reinforcement Learning

[PDF]When High ROC-AUC Fails: Score Collapse and the Gradient Exposure Deficit in Anomaly Detection

[PDF]Graphs are Evidence, Not Circuits

[PDF]When is Compositional Generation Feasible? Distributional Estimation Error and Inference-time Approximation Error in Diffusion Models

[PDF]Discovering Hierarchical Opponent Strategies via Structural Entropy Minimization in Imperfect-Information Games

[PDF]VibeVoice-ASR-Streaming: Who Spoke What in Real Time

[PDF]Efficient contextual partial monitoring with general function approximation

[PDF]Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?

[PDF]AESOP: Asymmetric Human-Camera Generation with Translation-Intensity Control

[PDF]Infinite From Finite: Recursive Basis Networks

[PDF]Selective Associative Memory: Rethinking the Representation Learner in Continuous-Time Time Series Forecasting

[PDF]What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrieval

[PDF]Learning What to Trust: Reliability-Conditioned Masked Modeling for Physiological Time Series

[PDF]From Skills to Stages: Stage-Aware Graph Retrieval for Relevant Skills in Large-Scale Agent Skill Libraries

[PDF]SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

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