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
2,061 results for “keyword:"benchmark"” in ICLR 2027. 508 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation▲9.2k2.67
[PDF]PVBench: Quantifying Physical Plausibility in Video Generation with Object-Level Physical Measurements▼4.5k2.67
[PDF]SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents▲432.75
[PDF]CARE-Med: A Capability-Resolved Benchmark for Medical Perception across Photographic and Physiological-Signal Images▲3.0k2.33
[PDF]Pix2Fact: When Vision Is Not Enough — Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes▼4.3k2.00
[PDF]MM-ImpBench: Measuring Multimodal Implicitness for Graded Evaluation of Vision–Language Models▼4.5k2.67
[PDF]ToolPlan-Bench: Diagnosing Hidden Planning Failures in Long-Horizon Tool-Calling Agents Beyond Success Rate▲3.9k1.75
[PDF]WAM-Bench: A Closed-Loop Benchmark for Open-Ended Instruction Following in Autonomous Driving▲4.7k3.25
[PDF]AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD▲3.0k2.33
[PDF]BREE: A Low-Cost, Fully Fabricable and Reproducible Platform for Real-World Bimanual Robotic Manipulation▲5.4k3.00
[PDF]The Geometry of AP Degradation: A Closed-Form, Zero-Parameter Theory of Localization Sensitivity▲5103.00
[PDF]LongHOI-Bench: Benchmarking and Improving Non-Contact Human-Object Interaction Understanding in MLLMs▲5103.00
[PDF]Unify ML4MILP: Disentangle, Recombine, and Reevaluate to Benchmark Neural Primal Heuristics with Solver-backed Search▲5103.00
[PDF]Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG▼4.3k2.00
[PDF]IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation▲3952.67
[PDF]RubricFly: Rubric-Guided Adaptive Evaluation and Judge Learning for Multilingual Translation▼4.3k2.00
Withdrawn or desk rejected (508)
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00