{"total":30,"rows":[{"id":"2404.02831","title":"Empowering Biomedical Discovery with AI Agents","created":"2024-04-03","cited_by_count":118,"area":null},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2410.04197","title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2404.13599","title":"\"A good pun is its own reword\": Can Large Language Models Understand Puns?","created":"2024-04-21","cited_by_count":21,"area":null},{"id":"2408.12128","title":"Diffusion-Based Visual Art Creation: A Survey and New Perspectives","created":"2024-08-22","cited_by_count":17,"area":null},{"id":"2505.16836","title":"Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning","created":"2025-05-22","cited_by_count":14,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2411.14205","title":"Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2411.00308","title":"GPT for Games: An Updated Scoping Review (2020-2024)","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2505.19236","title":"Evaluating Text Creativity across Diverse Domains: A Dataset and Large Language Model Evaluator","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2510.06231","title":"CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2402.11262","title":"Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima","created":"2024-02-17","cited_by_count":6,"area":null},{"id":"2506.01819","title":"Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2602.06423","title":"On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2604.25614","title":"HotComment: A Benchmark for Evaluating Popularity of Online Comments","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2509.25773","title":"v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2512.21494","title":"Oogiri-Master: Benchmarking Humor Understanding via Oogiri","created":"2025-12-25","cited_by_count":1,"area":null},{"id":"2604.09629","title":"HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2409.02291","title":"Initial Development and Evaluation of the Creative Artificial Intelligence through Recurring Developments and Determinations (CAIRDD) System","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2509.04779","title":"Decoders Laugh as Loud as Encoders","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2602.15842","title":"Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2604.15210","title":"Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.19786","title":"HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2608.04299","title":"Searching for Sound-Meaning Collisions: Graph-Based Affordance Retrieval and Multi-Evaluator Ranking for Pun Translation at CLEF 2026 JOKER Task 2","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.12475","title":"Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}