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
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
West Virginia University

ICLR 2027sort:activity acceptance volume newest

[PDF]KVFixer: Predictive KV Cache Repair for Context Revision

[PDF]Limits of Fixed Score Scaling in Diffusion Models under Gaussian Mixtures

[PDF]AgentTime: Can Agents Estimate and Control Their Own Runtime?

[PDF]TEMPORAL HYPERGRAPH JOINT- EMBEDDING PREDICTIVE ARCHITECTURE FOR MULTI-AGENT PATH FINDING

[PDF]A Dynamic Temporal Segmentation for Long Video Understanding

[PDF]Accumulation Is Maintenance: Anti-Preferential Placement and Online Structural Curation for Hierarchical Agent Memory

[PDF]MatchEdit: Matched-State Prompt Directions for Inversion-Free Flow-Based Image Editing

[PDF]Knowing What to Change Is Not Enough: State-Transition Locality in Foundation Models

[PDF]SkillPoison: Progressive Skill Poisoning via Successful Experiences

[PDF]From Decision Trees to Strong Reasoning Models for Tabular Data Classification

[PDF]Complete-Sample-Driven Shared Semantic Prototype Learning for Highly Incomplete Multi-View Clustering

[PDF]Universal In-Context Learning over Foundation Model Embeddings

[PDF]Conservation Is Not Allocation: Valuing Clients and Edges in Hierarchical Federated Learning

[PDF]Switching Theory for Q-Learning

[PDF]Measuring the stability of autoregressive generation: Paired latent trajectories under benign input perturbation

[PDF]Direct Latent Editing for VFM-Based Image Generators

[PDF]AVID: Benchmarking Audio-Visual Inconsistency Understanding for Omni-Modal Language Models

[PDF]When Are Safety Anchors Enough? Availability and Certified Preservation

[PDF]AVSG: Accelerated Vectorized Sparse Gather for Efficient KV Cache Offload in Sparse-Attention LLM Serving

[PDF]How Many Parameters Is a Trace Worth? Measuring Borrowed Capability in LLM Agents

[PDF]On the Low Rank Theory for the Data Shapley: Kernel Perspective

[PDF]Cross-Path Poisoning Attacks on Structured RAG

[PDF]Bridging Semantic Reasoning and Geometric Refinement with Diffusion Language Models for Multimodal 3D Human Pose

[PDF]Activation Factorization for Dense-to-MoE Conversion

[PDF]Prefix Semantic Dynamics in Long-Form Language Generation

[PDF]Revisiting Jigsaw Objectives for Fine-Grained Visual Representations

[PDF]Local Riemannian Stochastic Gradient Descent: Learning and Uncertainty Quantification

[PDF]Foresight on Demand: Learning What and When to Predict for Autonomous Driving

[PDF]AoG: Uncertainty-Guided Adaptive Reasoning Agent on Knowledge Graphs

[PDF]AgentSiphon: Privilege-Crossing Exfiltration through Covert Generation in RAG Agents

[PDF]Order-RFT: Gradient Alignment and Age-Aware Data Selection for Efficient Reinforcement Fine-Tuning

[PDF]Redundant Regulatory Programs Can Check Cell Groups They Locate Poorly

[PDF]Heavy-First, Light-Late: Reversing Capacity Scheduling for Efficient Video Diffusion

[PDF]PathwayFed: Disentangling Client-Specific Knowledge Pathways for Federated Multi-Label Learning

[PDF]Zero-Order Optimization via Learnable Direction Sampling for LLM Fine-Tuning

[PDF]Procedural Core: A Compact Recurrent Initialization for Vision Transformers

[PDF]Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory

[PDF]Every9D-22M: Large-Scale Real-World 9D Canonicalization of Everyday Objects

[PDF]Runtime-Adaptive Temporal Integration Improves Sparsity and Accuracy in Spiking Neural Networks

[PDF]Anderson Acceleration of Test-Time Training for Feed-Forward 3D Reconstruction

[PDF]Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows

[PDF]Sharp Root-Exponential Rates for Smooth Convex Optimization in a Serial Finite-Bit Model

[PDF]Banking Expiring Compute: How Reuse Shapes the Value of Prediction

[PDF]ECG-RePAIR: Agentic Test-Time Repair with Evidence Grounding for ECG Interpretation

[PDF]Quantize the Team: Joint Quantization and Topology Adaptation for Multi-Agent LLM Systems

[PDF]AutoCAST: Automated Character-Attributed Speech Transcription in Long-Form TV Dramas

[PDF]SWAN: Scaling Long-horizon World Models via Next-Scale Autoregression

[PDF]Bounded Contextual Refinement with Neighborhood Support for Text-Aerial Person Retrieval

[PDF]Initialization Shapes the Computational Regime of Adaptive Optimization

[PDF]DynaEval: Large Language Models Struggle to Track Evolving Task States

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