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]VISTA: Active Exploration for Self-Improvement in Embodied Agents22 $rep67%

[PDF]Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric Videos330 $rep67%

[PDF]RTSM: Adapting Recursive Models to Multivariate Time-Series Classification125 $rep67%

[PDF]Robust Recommendation under Unknown User Intent via Worst-Objective Optimization201 $rep67%

[PDF]LESS THAN MEETS THE EYE: ACTION-SET IDENTIFIABILITY AND PRINCIPLED ABSTENTION FOR 3D PHYSICAL GEOMETRY2 $rep67%

[PDF]Attribution Sensitivity Guided Parameter Allocation for Adversarially Robust Parameter-Efficient Fine-Tuning2 $rep67%

[PDF]Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections2 $rep67%

[PDF]LOOPED TRANSFORMERS LEARN ONE OF TWO ALGORITHMS, AND TRAINING MOVES THE ODDS102 $rep67%

S^{2}

Prompt: Sparse Semantic-to-Structural Prompting for Semi-Supervised Remote Sensing Segmentation146 $rep67%

[PDF]BEHAVIORAL TEST DIVERSITY: QUANTIFYING TEST SUITE DIVERSITY THROUGH AGENTIC CODE REPAIR21 $rep66%

[PDF]Self-Supervised Learning with Recursive Quadrature Filters for Neural Time Series2 $rep66%

[PDF]VISTA: Verifiable Self-Curriculum for Training GUI Agents2 $rep66%

[PDF]ECHO: A Hybrid Neural Operator For Coupled Thermo-Hydro-Mechanical Modelling In Enhanced Geothermal Systems2 $rep66%

[PDF]Population-Regularized Learning of Individualized Brain Effective Connectivity50 $rep66%

[PDF]The Cross-Entropy Gap: Scaling Laws for Sign and Gradient Descent21 $rep65%

[PDF]Cross-Entropy Guided Routing in Mixture-of-Experts Large Language Models99 $rep65%

[PDF]ReqMemBench: Benchmarking Coding Agents for Temporal Requirement-State Reconstruction in Evolving Projects201 $rep65%

[PDF]TimeSWARM: Soft Weighted Assignment-Based Relational Modeling of Channel-Patches for Multivariate Time Series Classification34 $rep64%

[PDF]SolidX: Learning Physical Interactions with Structured Bases for Multi-Solid Systems2 $rep64%

[PDF]A Finslerian Approach for Embedding Directed Data2 $rep64%

[PDF]ControlEdit: Image Editing with Unpaired Post-Training2 $rep64%

[PDF]Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving2 $rep64%

[PDF]Approximation Algorithms for Diversity-Aware

K

-Nearest Neighbor Search2 $rep64%

[PDF]Quotient-First Decoding: Sharp Truncation Gaps Without Support Loss2 $rep64%

[PDF]JEDI: Jointly Embedded Inference of Neural Dynamics2 $rep64%

[PDF]Sub-Patch Semantics in DINOv3: Geometry, Recoverability, and Feature Upsampling2 $rep64%

[PDF]COMPASS: Routing via Capability-Oriented Model Profiling with Adaptive Search, Selection, and Tool Use2 $rep64%

[PDF]TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation51 $rep64%

[PDF]Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning25 $rep63%

[PDF]AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks201 $rep63%

[PDF]SEAL: Statistical Embedding Alignment for Code Watermarking2 $rep63%

[PDF]DAKF: Tracking Nonstationary Dynamics with Precision-Weighted Excitation2 $rep63%

[PDF]The Executable Content of Gibbs Path Tilts2 $rep63%

[PDF]Recurrent Reasoning with Fixed Point Attention50 $rep63%

[PDF]RAA-PINN: Residual Anti-Aliasing for Physics-Informed Neural Networks202 $rep63%

[PDF]Pitfalls of Evaluating Graph Foundation Models for Node Property Prediction189 $rep63%

[PDF]DistillTrace: Tracing LLM Distillation via Keyed Solution Preferences102 $rep63%

[PDF]Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency2 $rep62%

[PDF]Looped Reasoning Finishes Earlier Than You Think79 $rep62%

[PDF]Diffusion-Guided Elite Path Inpainting for 3D Electromagnetic Coil Initialization2 $rep62%

[PDF]LoCoFlow: Local-Context Flow Matching for Single-Cell Dynamics and Fate Inference151 $rep62%

[PDF]WaveFormer: A Behavior-Aware Transformer for Analog Performance Prediction Via Circuit Response Pretraining102 $rep62%

[PDF]AD-DHGNN: Adaptive Dual-Controlled Dynamic Hypergraph Neural Networks12 $rep62%

[PDF]The Many Faces of Short Convolutions in Transformers122 $rep62%

[PDF]HyperGCN-Vessel: Hybrid Geometric Representation Learning for Topology-Preserving Vascular Segmentation2 $rep62%

[PDF]Beyond Gaussian Assumptions: Distribution-Aware Channel Capacity for Effective Connectivity2 $rep62%

[PDF]TextualRL: Textual Reinforcement Learning for Context Management2 $rep62%

[PDF]Risk-Controlled Personalized Popularity Alignment for Frozen Collaborative Filtering201 $rep62%

[PDF]Peering over the Manifold Vistas: A Unified Geometric Framework for Counterfactual XAI51 $rep62%

[PDF]PonderLM-3: Token-Adaptive Pondering with Differentiable Masking51 $rep62%

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