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
346 results for “keyword:"benchmarking"” in ICLR 2027. 77 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ESUN-Bench: A Workload-Aware Benchmarking Framework for Ethernet-Based Scale-Up AI Fabrics▼1361.33
[PDF]Are LLM Agents Long-Termist? Evaluating Long-Horizon Resource Optimization in Roguelike Environments▼1361.33
[PDF]StatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive Software▼5.8k2.33
[PDF]ManiGuard: A Specification-Grounded Framework for Safety Evaluation and Demonstration Generation in Robotic Manipulation▼4.3k2.00
[PDF]EarlyKnowBench: When Does a Gui Agent Know What the User Wants, and Does It Keep Knowing?▼11k2.33
[PDF]Watt Does a Benchmark Point Cost? Measuring the Energy Efficiency of LLM Capability under Production Serving▲3.0k2.33
[PDF]QuantaMind: A Large Chemistry Language Model for Structured Molecular Screening and Discovery▼1361.33
[PDF]OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation Scenarios▲3.0k2.33
[PDF]What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents▼1.3k1.80
[PDF]Safe in Text, Unsafe in Action: Distinguishing Content and Physical Danger in LLM Hidden States▼4.5k2.67
[PDF]Moderating Covertly Sensitive Images Across Policies: Policy-Reconfigurable Benchmark and Zero-Shot Method▼1.2k1.67
[PDF]After the Second Bell: Can Audio-Language Models Reason with Temporally Grounded Events?▼1.3k1.80
[PDF]Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?▲14k3.00
[PDF]AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification▲3952.67
[PDF]AmbiguityBench: Reasoning Modes Bidirectionally Shift Ambiguity Sensitivity in Frontier LLMs▼1.2k1.67
[PDF]MM-ImpBench: Measuring Multimodal Implicitness for Graded Evaluation of Vision–Language Models▼4.5k2.67
[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]SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown▼5.8k2.33
Withdrawn or desk rejected (77)
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00
[PDF]A Thousand Faces: A Persuasion Benchmark with Experience-Grounded Persuadees Informed by Psychology and PragmaticsWithdrawn1.67
[PDF]CORE-CVR: Benchmarking Fine-grained Reference Understanding in Composed Video RetrievalWithdrawn2.00
[PDF]When Tools Dominate, When Strategies Matter: A Causal Study of Agentic Computational BiologyDesk rejected1.33
[PDF]One Relation Is Not Enough: Benchmarking Relational Spatial Understanding in Vision-Language ModelsWithdrawn1.67
[PDF]Diagnosing and Advancing Long-Video Understanding for Distributed Evidence CompositionWithdrawn1.67