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240 results for “keyword:"math"” in ICLR 2027. 35 withdrawn or desk rejected listed apart.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]ProbePO: Sparse Probes, Redistributed Credit for Critic-Free LLM Reinforcement Learning▼4.5k2.67
[PDF]SELD: Selective On-Policy Distillation for Mathematical Reasoning via Semantic Error Localization▼4.3k2.75
[PDF]TraceStencil: Signed Temporal Neighborhoods for Token-Level Policy Optimization in RLVR▼1.2k1.67
[PDF]ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning▲3.0k2.33
[PDF]HEIR: When the Student Inherits the Teacher's Seat Pareto-Competitive Reference Selection for On-Policy Self-Distillation of Reasoning LLMs▼5.3k1.33
[PDF]Revisiting Mathematical Reasoning Verification with Deep-Research-Grounded Trajectory Distillation▼1.2k1.67
[PDF]Capability Budgeting: Acquiring Mathematical Reasoning While Retaining Capabilities in Multilingual Continual Pretraining▼1.3k1.75
[PDF]Where Should Suppressed Probability Go? One-Step Lookahead KL Routing for On-Policy Distillation▲6.1k2.00
[PDF]SketchForge: Prover-Guided Reinforcement Learning for Sketch Generation in Agentic Theorem Proving▼4.3k2.00
[PDF]LinAlg-Bench: When LLMs Stop Computing — Structured Hallucination, Sign Drift, and Depth-Gated Collapse in Matrix Arithmetic▲11.00
[PDF]Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics▼1361.33
[PDF]Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training▼1.2k1.67
Withdrawn or desk rejected (35)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