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 in each venue. 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

Aalto University
Virginia Tech
Roche
Indian Institute of Technology Kharagpur
Korea Advanced Institute of Science and Technology
ETH Zurich
The Chinese University of Hong Kong
Carnegie Mellon University
New York University
Indian Institute of Technology Dhanbad
École Polytechnique
University of Delaware
Mohamed bin Zayed University of Artificial Intelligence
University of Moratuwa
INHA University
Indian Institute of Technology Delhi
Emory University
Johannes Kepler University of Linz
Industrial University of Santander
École Polytechnique Fédérale de Lausanne
West Virginia University
Ludwig-Maximilians-Universität München
University of California, Irvine
Pohang University of Science and Technology
Amazon
Los Alamos National Laboratory
北京大学
ELLIS Institute Tübingen
École Nationale Supérieure de Techniques Avancées
University of Maryland, College Park
University of Surrey
Georgia Institute of Technology
University of California, Santa Barbara
University of Pennsylvania
Uppsala University
Delhi Technological University
National Taiwan University
University of California, Los Angeles
University of California, Berkeley
United International University
University of California San Diego
Mila
University of Southern California
Harvard University
Polytechnique Montréal
Massachusetts Institute of Technology
University of Tübingen
Shanghai Jiao Tong University
Technical University of Munich
Birla Institute of Technology and Science, Pilani – Pilani Campus
University of Illinois Urbana-Champaign

Aalto University
Virginia Tech
Roche
Indian Institute of Technology Kharagpur
Korea Advanced Institute of Science and Technology
ETH Zurich
The Chinese University of Hong Kong
Carnegie Mellon University
New York University
Indian Institute of Technology Dhanbad
École Polytechnique
University of Delaware
Mohamed bin Zayed University of Artificial Intelligence
University of Moratuwa
INHA University
Indian Institute of Technology Delhi
Emory University
Johannes Kepler University of Linz
Industrial University of Santander
École Polytechnique Fédérale de Lausanne
West Virginia University
Ludwig-Maximilians-Universität München
University of California, Irvine
Pohang University of Science and Technology
Amazon
Los Alamos National Laboratory
北京大学
ELLIS Institute Tübingen
École Nationale Supérieure de Techniques Avancées
University of Maryland, College Park
University of Surrey
Georgia Institute of Technology
University of California, Santa Barbara
University of Pennsylvania
Uppsala University
Delhi Technological University
National Taiwan University
University of California, Los Angeles
University of California, Berkeley
United International University
University of California San Diego
Mila
University of Southern California
Harvard University
Polytechnique Montréal
Massachusetts Institute of Technology
University of Tübingen
Shanghai Jiao Tong University
Technical University of Munich
Birla Institute of Technology and Science, Pilani – Pilani Campus
University of Illinois Urbana-Champaign

sort:activity odds

[PDF]STREAM: Sample-Adaptive Two-level Routing Experts with Aligned Mamba for Multimodal Representation Learning

[PDF]Joint Conformal Source Localization: Source Set Inference and Order-Adaptive Set Scoring

[PDF]WithinVAE: Compact Visual Autoencoding with Self-Distilled Semantics

[PDF]Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Models

[PDF]Safety in Numbers: The KV Cache Was Never That Fragile to Repeated Pruning

[PDF]SCAS: Symmetrical Concept-space Activation Steering for Joint Hallucination Mitigation and Capability Enhancement in VLMs

[PDF]Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild

[PDF]EHRGym: A Diagnostic Benchmark for Offline Reinforcement Learning

[PDF]VideoPursuit: From Retrieval Actions to Local Retrieval Processes for Agentic Long-Video Understanding

[PDF]Evaluating LLM Reasoning Beyond Correctness

[PDF]Conformal Elicitation: Loss Minimization Controls Set Size Regret

[PDF]Hierarchical Masked Diffusion Language Model

[PDF]Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space

[PDF]Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning

[PDF]Learning to Draw Interfaces: What Makes Synthetic UI Data Work for Text-to-Image Models

[PDF]COVE: Concept Vocabulary Evolution for Streaming Continual Visual Instruction Tuning

[PDF]Co-Harness: Collective Harness Evolution for Agentic Multimodal Large Language Model

[PDF]LUSim: An LLM-Driven Spatial-Equilibrium Simulator for Urban Planning

[PDF]Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

[PDF]ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception

[PDF]Beyond Refusal Rates: How SFT and RL Shape LLM Safety Discernment

[PDF]Less Data, Better Timing: Student–Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding

[PDF]Scaling Domain Data Repetition in LLM Pretraining

[PDF]One Model, Many Depths: A Recipe for Elastic-Depth Latent Recurrent Language Models

[PDF]COMPUTING GUIDANCE SCHEDULES FROM CONDITIONAL INFORMATION IN MASKED GENERATIVE MODELS

[PDF]Next Demonstration Prediction for Visual In-Context Learning

[PDF]What to Teach Before Acting: Revisiting Embodied VQA for VLA Models

[PDF]LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation

[PDF]Skills and Challenges Co-Evolve: Learnability-Aware Autocurricula for Agent Skill Evolution

[PDF]ReScraper: Unified Scraping and Cleaning of Web Data for Effective LLM Pretraining

[PDF]HYSGUARD: RESETTING SAFETY STATE, NOT GENERATION, FOR STREAMING LLM SAFEGUARDS

[PDF]xRRMs: Explorative Recurrent Reasoning Models

[PDF]WikiEvolve: Coupling Foundational and Experiential Knowledge in Self-Evolving Agents

[PDF]Distill the Teacher, Credit the Action: What On-Policy Distillation Transfers to a Visual Agent's Actions

[PDF]Detect-Then-Adapt: Continuous-Stream Neural Decoding for Online Adaptation

[PDF]Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation

[PDF]Self-Evolution Should Be Stable, Not Frozen: Lyapunov-Gated Recursive Self-Improvement

[PDF]Less Text, More Evidence: Static Pruning and the Coverage Paradox in Language Models

[PDF]Klein Flow Matching in Hyperbolic Latent Space

[PDF]NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters

[PDF]Differential Attention for State Space Models

[PDF]JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space

[PDF]ANGULAR REACHABILITY REPRESENTATIONS FOR OFFLINE GOAL-CONDITIONED REINFORCEMENT LEARNING

[PDF]LMSysDojo: Building Scalable Analytical Agents for Optimizing Complex LLM Serving Systems

[PDF]Multi-anchor QK-coupling in LLMs: Shared Attention Routing and Efficient Learning

[PDF]MARS: Multi-Evidence Adaptive Search with State-Preserving Control for Repository-Level Program Repair

[PDF]Learning Individual Scientific Taste with Privileged Hindsight Distillation

[PDF]DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

[PDF]SUPERVISION BEFORE STRUCTURE: WHAT A WORLD MODEL NEEDS TO KNOW WHAT IT CANNOT ANSWER

[PDF]Distance is More Than a Bias: Geometry-Driven Value Mixing in Graphs

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