{"total":16,"rows":[{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2512.04062","title":"Eval Factsheets: A Structured Framework for Documenting AI Evaluations","created":"2025-12-03","cited_by_count":9,"area":null},{"id":"2512.02942","title":"Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench","created":"2025-12-02","cited_by_count":7,"area":null},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2602.00249","title":"SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2505.06803","title":"Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2511.19647","title":"Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2605.24981","title":"Large Language Model Selection with Limited Annotations","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.03715","title":"Text-to-Image Models Need Less from Text Encoders Than You Think","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2504.06313","title":"Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activities","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2506.02027","title":"The End Of Universal Lifelong Identifiers: Identity Systems For The AI Era","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2509.17907","title":"MEF: A Systematic Evaluation Framework for Text-to-Image Models","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.09418","title":"Large Language Model Selection with Limited Annotations","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.20482","title":"Reliable and Reproducible Demographic Inference for Fairness in Face Analysis","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2603.22249","title":"EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild","created":"2026-03-23","cited_by_count":0,"area":null}],"next_cursor":null}