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]WaveFormer: A Behavior-Aware Transformer for Analog Performance Prediction Via Circuit Response Pretraining100 $rep62%

[PDF]AD-DHGNN: Adaptive Dual-Controlled Dynamic Hypergraph Neural Networks10 $rep62%

[PDF]The Many Faces of Short Convolutions in Transformers120 $rep62%

[PDF]Risk-Controlled Personalized Popularity Alignment for Frozen Collaborative Filtering199 $rep62%

[PDF]Peering over the Manifold Vistas: A Unified Geometric Framework for Counterfactual XAI49 $rep62%

[PDF]PonderLM-3: Token-Adaptive Pondering with Differentiable Masking49 $rep62%

[PDF]How to catch distillation135 $rep61%

[PDF]Unmergeable LoRA: Proactively Protecting Adapters from Unauthorized Merging321 $rep61%

[PDF]Tokenisation via Convex Relaxations31 $rep61%

[PDF]Anchored Scenario Coverage for Failure-Aware First-Hit Batch Inverse Design199 $rep60%

[PDF]Agentic Critical Training48 $rep59%

[PDF]Towards Merging-conditional Backdoor Unalignment against Large Language Models241 $rep59%

[PDF]Gradient-Free Sampling from Generative Models via Stochastic Bounded Extremum Seeking100 $rep59%

[PDF]Privacy Admission from Incomplete Rényi Differential Privacy Histories149 $rep58%

[PDF]MAGE: Matrix-weighted Attention Graph Energies for LLM Family Fingerprinting39 $rep55%

[PDF]OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning100 $rep54%

[PDF]QReS: Quantizing Recurrent Language Models Is Easier Than You Think327 $rep52%

[PDF]HazeMT-DCR: Demand-Aware Counterfactual Expert Routing for Incremental Multi-Task Prediction in Hazy Scenes46 $rep52%

[PDF]Meta²: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents210 $rep51%

[PDF]LUCID: Universal Auditing of Distilled Large Language Models235 $rep49%

[PDF]SAAC: Sizing Agent for Analog Circuit via Turn-Level Reinforcement Learning100 $rep49%

[PDF]Training-Free Protection of LLMs against Unauthorized Model Merging232 $rep45%

[PDF]Distillation Lineage Inspector: Black-Box Auditing of Model Distillation in LLMs140 $rep41%

[PDF]Interpretable Feature Discovery from Unstructured Data Using LLMs and Statistical Choice Models1,902 $rep41%

[PDF]BioMetaEvo-GNN: Bayesian Fourier Message Passing with Immune Memory for Robust Community Detection58 $rep39%

[PDF]SPEF: Semantic Prior-Selected Expert Fusion for Working-Memory Prediction from Multimodal Brain Connectomes100 $rep35%

[PDF]DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization199 $rep32%

[PDF]SMS-Sizing: An Agentic Search Framework for Feasible Analog Circuit Sizing and Archive Expansion100 $rep25%

[PDF]Stop Blaming Aggregation in Deep GNNs Based on Incomplete Evidence209 $rep12%

[PDF]Layered Game Engine: A Compositional Architecture for Executable Game Worlds19 $rep12%

[PDF]Real-Time Causal Dynamics on Geometric Latent Spaces for Precision Therapeutic Monitoring35 $rep11%

[PDF]When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero42 $rep7%

[PDF]Continual Calibration: Stale Conformal Thresholds Fail Under Lifelong LLM Fine-Tuning

[PDF]LARA: Language-Adaptive Reward-Anchored Preference Optimization

[PDF]Not All Tokens Are Equal: Entropy-Guided Credit Assignment for Direct Preference Optimization

[PDF]On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models

[PDF]SELECTION-SAFE CONFORMAL EARLY EXIT: DISTRIBUTION-FREE COVERAGE UNDER ADAPTIVE DEPTH

[PDF]A Narrow Residual Bottleneck from Evidence to Answer in Language Models

[PDF]ActTime: Action-Conditioned World Modeling for Time Series

[PDF]BlockFAMQ: Realized-Residual Curvature for Complete-Checkpoint Mamba Quantization

[PDF]ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model

[PDF]ReRank-TTA: Learning to Rerank at Test Time for Robust Text Recognition

[PDF]Before Answering: Evidence Sufficiency under Size-Matched Memory Construction

[PDF]What Intervention Loss Certifies: Sharp Bounds for Factor Separation

[PDF]When Does Query-Aware Quantization Help? From Redundancy In-Distribution to Gains in Multimodal Retrieval

[PDF]SURE-Bench: Sensor Understanding and Reasoning with Evidence Benchmark for Human Activity

[PDF]MORPHOT: Evaluating Morphologically Rich Indic Languages with Hierarchical Unbalanced Optimal Transport

[PDF]MRT: Regularizing Tokenization with Morphology for Low-Resource Indic Languages

[PDF]PointDex: Dexterous Grasp Generation via Point-based Hand-Object-Contact Modeling

[PDF]TriFactorHOI: Structured Diffusion for Controllable and Contact–Consistent Human–Object Interaction Synthesis

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