NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
240 results for “keyword:"math"” in ICLR 2027. 35 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Reviewers Catch and Frontier Models Miss: Statement-Level Errors in Autoformalization▲6.1k2.00
[PDF]Standard Data Scaling Analyses Obscure Loss of Important Information in Math Reasoning▼4.3k2.00
[PDF]Distilling Structure, Not Solutions: Structural Bottlenecks for On-Policy Self-Distillation▼4.3k2.00
[PDF]TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning▲6.1k2.00
[PDF]TCSALGBENCH: BENCHMARKING AUTOMATED PROVING FOR RESEARCH-LEVEL THEORETICAL COMPUTER SCIENCE▲5.4k3.00
[PDF]Rewarding the Graph Behind the Chain: Topology-Aware Process Supervision for RL and Reasoning Distillation▲3972.67
[PDF]Every Fork Has a Price: The Precision–Coverage Trade-off in On-Policy Distillation of Reasoning Models▼1.2k1.67
[PDF]The Primitive Recursor Test: Construction-Recognition Gap and Representation-Shift Failure in Formal Reasoning▼4.3k2.00
[PDF]Improving the Credit Assignment of Group Relative Policy Optimization via λ-Return Advantage Estimation for LLM Reasoning▼1.2k1.67
[PDF]When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling▼4.3k2.00
[PDF]Small Steps on the Geodesic: Ability-Anchored Progressive Curricula for RL on Reasoning▼5.8k2.33
[PDF]Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance▲5103.00
[PDF]A Claim-Centered Publication Framework for Efficient Auditing of AI-Assisted Theoretical Research▼4.3k2.00
[PDF]DiffMath: Symbol- and Graph-Aware Latent Diffusion Transformer for Handwritten Mathematical Expression Generation▼4.5k2.67
[PDF]Sampling Versus Longer Responses for Visual Reasoning: A Matched-Prompt MathVista Study▼1361.33
[PDF]Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics▼5.8k2.33
[PDF]SolidGeoGen: Advancing Multimodal Solid-Geometry and Spatial Reasoning through Verifiable Symbolic Generation▲3972.67
[PDF]The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models▼2433.33
Withdrawn or desk rejected (35)
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]STEP: From Local Teacher Scaffolds to Student-Owned Reasoning in Small Language ModelsDesk rejected