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

ICLR 2027sort:acceptance volume activity newest

[PDF]Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity300 $rep93%

[PDF]Rank Confidence Sequences: Anytime-Valid Leaderboards100 $rep91%

[PDF]How Does "English (US)” Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline100 $rep90%

[PDF]DisContact: Generating Hand Motion and Discrete Contact Maps with Geometry-Coupled Hybrid Diffusion15 $rep89%

[PDF]When Is One Reading Enough? Decision-Relevant Ambiguity in Constrained Reinforcement Learning200 $rep89%

[PDF]Back to the Roots? Rethinking Multilingual LLMs through Foundational Learner Vocabulary100 $rep88%

[PDF]CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles100 $rep88%

[PDF]Automated Circuit Discovery for Equivariant Molecular Networks100 $rep88%

[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety Evaluation16 $rep88%

[PDF]PACE: A Reinforcement-Learning Agent for Accelerated 3D Gaussian Splatting100 $rep88%

[PDF]Extending SSMs with the Exponentially Weighted Signature100 $rep87%

[PDF]Green-Routed Neural Operators: Physics Determines Where the Network Reads159 $rep86%

[PDF]Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models500 $rep86%

[PDF]LinQuant: Functional Invariances for Low-Precision Linear Recurrences285 $rep86%

[PDF]Thinking with Looped Flows19 $rep86%

[PDF]H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache19 $rep86%

[PDF]MOSAIC: Multi-task Orchestration via Sparse Atomic Interpolated Control19 $rep86%

[PDF]Interaction-Aware Influence Functions for Group Attribution154 $rep86%

[PDF]SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining21 $rep86%

[PDF]VioLA: Learning Generalist Humanoid Control Policies from Human Data701 $rep85%

[PDF]Grounded World Model: Latent Planning with Language Goals140 $rep85%

[PDF]AGI-TPT: Adaptive Geometry-Informed Test-Time Prompt Tuning for Calibrated Zero-Shot Vision-Language Models19 $rep85%

[PDF]Premise over Pixels: Diagnosing Visual Self-Correction in Vision-Language Models19 $rep85%

[PDF]Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering19 $rep85%

[PDF]Styling Past the Guard: Content-Preserving Style Attacks on VideoLLM Pipelines19 $rep85%

[PDF]ISCon: A Theoretical Framework for Testing Design Rationales of Personalization Models19 $rep85%

[PDF]Watermark Basins: Black-Box Detection of Distilled LLMs111 $rep85%

[PDF]A Foundation Model for Time-Harmonic Electromagnetic Behavior46 $rep85%

[PDF]ChronoSync: Recovering Long-Horizon Coupled Dynamics via Cross-Field Synchronization of Decoupled Diffusion Models22 $rep85%

[PDF]Visual Abstention in Unified Multimodal Models42 $rep84%

[PDF]SAVER: Sequential Anytime-Valid Editing Risk-control in Large Language Models100 $rep84%

[PDF]Spatial-as-Refinement: Gated Graph Operators over Strong Temporal Predictors for Scalable Spatio-Temporal Forecasting49 $rep84%

[PDF]The Floor That Barely Falls: Untrained Encoders as the Operative Null for Concept-Discovery Metrics220 $rep83%

[PDF]Early Warning of Personalization Model Degradation from User Histories and Hidden States199 $rep83%

[PDF]Multiphysics Post-Training: From Decoupled Modules to Coupled Equilibria18 $rep83%

[PDF]hyperSMARTIES: Physics-Aware Spectral Representation Learning for Remote Sensing400 $rep83%

[PDF]Leaderboards Display Ranks, Benchmarks Certify Tiers: Simultaneous Inference and a Capacity Law for LLM Evaluation49 $rep83%

[PDF]Tracing Influence: Unboxing LLM Outputs with Sparse Latent Spaces245 $rep82%

[PDF]Mask Components, Not Bands: Rethinking Masked Autoencoding for Hyperspectral Imagery19 $rep82%

[PDF]When Tools Fail Quietly, LLM Agents State Wrong Answers as Fact100 $rep82%

[PDF]Quantizing Recursive Reasoning Models50 $rep82%

[PDF]Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow100 $rep82%

[PDF]Planetary Feature Fields are Scalable Earth Representations200 $rep82%

[PDF]SSA: Scaled Sink Attention for Large Language Models99 $rep81%

[PDF]FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL42 $rep81%

[PDF]GMNO on MaxwellBench: Scaling Pretrained General Mesh Neural Operator Across Industrial-Standard Electromagnetism Simulations19 $rep81%

[PDF]Project Before You Distill: Carrying Privileged Chain-of-Thought Across Sensor Gap1 $rep81%

[PDF]Learning When to Trust PDE Coupling Priors in Neural Operators48 $rep81%

[PDF]Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue84 $rep81%

[PDF]End-to-End Differential Privacy for Multi-stage Foundation Model Training127 $rep81%

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