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
[PDF]DyStream: Streaming Dyadic Talking Heads Generation via Flow Matching-based Autoregressive Model23 $rep76%
[PDF]Forgotten or Inaccessible? Restoration Savings Reveal What Language Models Retain After Fine-Tuning100 $rep76%
[PDF]Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does19 $rep75%
[PDF]You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs409 $rep75%
[PDF]Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?19 $rep74%
[PDF]BeaconAgent: Learning Capability-Aware Help-Seeking Policies for Small Language Model Agents199 $rep74%
[PDF]RANK IS NOT A TRUST REGION: OPTIMIZER-INDUCED GEOMETRY IN LORA REINFORCEMENT LEARNIN134 $rep74%
[PDF]AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness100 $rep74%
[PDF]VISTA: Learning Wide Search Agents with Verifiable Intermediate States and Turn-Level Credit Assignment147 $rep73%
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layers700 $rep73%
[PDF]GLoDe: Global–Local Decomposition for Histology-based Spatial Gene Expression Prediction44 $rep73%
[PDF]SPIRA: A Spatially-Variant Reinforcement-Learning Agent for Unsupervised Imaging Inverse Problems100 $rep73%
[PDF]VISTA: A Multimodal Egocentric Benchmark for Goal-Oriented Perception and Assistance to Blind and Low-Vision Users20 $rep73%
[PDF]Web2LongTraj: Scaling Long-Horizon Agent Trajectories from Natural Web Corpora for Mid-Training226 $rep72%
[PDF]Commit Order, Not Commit Rate: Answer Availability and Prefix Preservation in Diffusion Language Models100 $rep72%
[PDF]RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models19 $rep72%
[PDF]Entropogram-Guided Visual Realignment Decoding: Capturing the Rhythm of Multimodal Reasoning199 $rep72%
[PDF]GraphFM: Graph-Constrained Flow Matching for Dynamics Reconstruction from Temporal Snapshots93 $rep72%
[PDF]Depth-Resolved Gene Expression Estimation from Tissue Morphology and Sparse Spatial Transcriptomics36 $rep71%
1 If this project is interesting to you, reach out at [email protected].