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
2,518 results for “area:"datasets and benchmarks"” in ICLR 2027. 617 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RAF: RUBRICS AUTO-GENERATION FRAMEWORK FOR AUDITABLE EVALUATION OF LONG-HORIZON LLM AGENTS▼4.3k2.00
[PDF]PhyAudioBench: Benchmarking Physical Consistency in Audio Generation through Controlled Interventions▼1361.33
[PDF]1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World▼5.8k2.33
[PDF]Can the Simulated Student Learn? Fitted Knowledge-Tracing Models Disagree on Spacing, Recency and Transfer▲11k2.00
[PDF]True Quotes, False Impressions: A Benchmark for Adversarial Extractive Summarization on Long-Document Classification▼4.3k2.00
[PDF]OpenRCA 2.0: Benchmarking Process Level Incident Root Cause Analysis for Microservices▼5.8k2.33
[PDF]MolDeTox: Evaluating Language Model’s Stepwise Fragment Editing for Molecular Detoxification▼4.3k2.00
[PDF]Diagnosing Temporal Instance-State Binding and Its Stage-Dependent Repairability in Vision-Language Models: A Controlled Study▼5.8k2.33
[PDF]ID2C: EVALUATING AND ADVANCING DOCUMENT-TO-CHART GENERATION WITH IMPLICIT REQUIREMENTS▲6.1k2.00
[PDF]VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification▲5103.00
[PDF]BodyBound: A Benchmark for Diagnosing Robot-Policy Responses to Body Changes Beyond Task Success▼1.2k1.67
[PDF]Diversity Is Measured, Not Assumed: Generating Memory Evaluations from Real Order Histories▼1361.33
[PDF]AudCraft: Understanding the Audience-Oriented Creation Gap Between Human Creators and LLMs with Real-World Platform Data▲5.4k3.00
[PDF]From Seeing to Solving: Benchmarking and Diagnosing Symbolic Reasoning in Large Vision-Language Models▲9.2k2.67
[PDF]What-If World: A Contrastive Reasoning Benchmark for Video World Models in Embodied Scenarios▼4.5k2.67
[PDF]When the Harness Confirms the Hypothesis: Silent Configuration Faults in Multi-Agent LLM Evaluation▼1361.33
[PDF]ARCUS-X: Adaptive Rule Compliance Under Sequential eXecution for Long-Horizon Language Model Evaluation▼4.3k2.00
[PDF]What Can Large Language Models Discover from Experiments? Scientific Claims and Discovery Value across Multiple Worlds▼1611.50
[PDF]Compression Is Not Evaluation-Neutral: Fixed RAG Compression Can Distort Reader Comparisons▼1361.33
[PDF]IMUHand Benchmark:A Dataset and Baseline for 3D Hand Motion Reconstruction from Sparse IMUs▲5.4k3.00
[PDF]CONTACT: A Human-Grounded Benchmark and Surprisal-Based Predictive Scorer for Conversational Naturalness▲13k2.33
Withdrawn or desk rejected (617)
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Matched Counterfactual Attribution: A Controlled Evaluation of Data Selection for Video Instruction TuningDesk rejected2.00
[PDF]Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction TuningDesk rejected1.67
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected