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]DualFuture: Event-Triggered Dual-Future Residual Correction for Vision-Language-Action Policies

[PDF]Structural re-parameterization is not magic

[PDF]Seemingly Shallow Priors Are Sufficiently Expressive for Asymptotically Bayes Optimal Multiple Testing under Sparsity

[PDF]ReMoVe: Refining a Video Model's Own Motion for Coherent Human Video Generation

[PDF]SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability

[PDF]The Sigmoid Strikes Back

[PDF]LatentWeave: Learning High-Value Thought for Efficient Visual Reasoning

[PDF]ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use

[PDF]Situated Inference: Adapting Frozen Generative Speech Enhancement under Acoustic Distribution Shift

[PDF]AIM: Agentic Idea Management for Automated Research

[PDF]Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing

[PDF]Making Generalized Category Discovery Useful for Biodiversity Monitoring

[PDF]Master-and-Stop Training for Out-of-Distribution Detection

[PDF]RNAClip: Auxiliary Protein–Ligand Data Improves Pocket-Free RNA–Ligand Virtual Screening

[PDF]What Accuracy Hides In Learned Transformer Programs

[PDF]Recovery over Agreement: Cross-View Masked Graph Learning for Drug Repositioning

[PDF]When One Direction Is Not Enough: GRASP for Conditional Activation Steering

[PDF]Beyond One-Step Accuracy: State-Affine Latent Transition for Reliable Visual Planning

[PDF]TIDIER: Text-to-Image Alignment via Knowledge-Guided Hate Detection, Interpretation, and Repair

[PDF]TC-NMD: Trajectory-Conditioned Non-Markovian Diffusion for DNA Sequence Design

[PDF]The Knowledge Is Already There: Geometric Interventions for Factual Recall in LLMs

[PDF]UniGenStereo: Unified Stereo Video Generation with Flexible Conditioning

[PDF]SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning

[PDF]Not in Isolation: Learning from Scene Dependencies for Open-Vocabulary Remote Sensing Segmentation

[PDF]LAM-RAG: LoRA Messages for Multi-Document Retrieval-Augmented Generation

[PDF]CtrlRecon: Steering Expressive Human Reconstruction toward Prescribed States

[PDF]Towards General Real-World Image Restoration: AIGC-Supervised Learning with Knowledge Distillation

[PDF]RL-Guided Mid-Training for Iterative LLM Evolution

[PDF]AgeALBench: Benchmarking Deep Active Learning for Facial Age Estimation with Crowd-sourced Annotations

[PDF]Geometric Flow Matching for Learning Quantum Many-Body States with Classical Shadows

[PDF]Inferring Objects Around Corners from Indirect Wall Light: Structure-Preserving Silhouette Recovery with RUBIN

[PDF]Manifold-DETR: Local Manifold-Aligned Attention for Object Detection

[PDF]Multiverse Bayesian Optimization with Joint Finite-Feature Surrogates

[PDF]AdaDim: Dimensionality Adaptation for SSL Representational Dynamics

[PDF]Beyond Speaker Verification: Speaker Embeddings for Perceptual Similarity

[PDF]Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation

[PDF]CogRef: Cognitive Reflection for Hallucination Mitigation in Multimodal Large Language Models

[PDF]Plug, Play, or Re-Evaluate: Harness Components Across Models

[PDF]HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction

[PDF]HalluGuard: Decoupled Automatic Hallucination Detection and Mitigation in MLLMs

[PDF]Robust Information-Gain Control Active Agentic Reasoning under Approximate Beliefs

[PDF]Geometry-Aware Diffusion Guidance via Curvature-Adaptive Tubular Correction

[PDF]CoMem: Compounding Retrieved and Parametric Memory for Reflective Language Agents

[PDF]EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

[PDF]Trust Before Autonomy: Pre-Outcome Selective Routing for Coding Agents

[PDF]CellShift: Benchmarking Single-Cell Temporal Models on Unseen Biology

[PDF]MAD-HOI: Masked Autoregressive Diffusion for Generating Articulated Hand Object Interactions from Text

[PDF]Hybrid SE-PG: Reliable Gradient Estimation in Pre-Convergence Differentiable Optimization

[PDF]Separating Detection from Repair in Long-Horizon Manipulation

[PDF]DDSeVA: Demand-Driven Semantic Value Navigation with Verified Target Acquisition

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