{"total":98,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286,"area":"lr"},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125,"area":"lr"},{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102,"area":"mllm"},{"id":"2404.11757","title":"Language Models Still Struggle to Zero-shot Reason about Time Series","created":"2024-04-17","cited_by_count":88,"area":"lr"},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77,"area":null},{"id":"2312.02439","title":"Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation","created":"2023-12-05","cited_by_count":56,"area":"lr"},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2501.05435","title":"Neuro-Symbolic AI in 2024: A Systematic Review","created":"2025-01-09","cited_by_count":38,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2311.09682","title":"MacGyver: Are Large Language Models Creative Problem Solvers?","created":"2023-11-16","cited_by_count":34,"area":null},{"id":"2310.11158","title":"Probing the Creativity of Large Language Models: Can models produce divergent semantic association?","created":"2023-10-17","cited_by_count":33,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","cited_by_count":22,"area":null},{"id":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"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":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19,"area":"mllm"},{"id":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19,"area":"alignment"},{"id":"2409.13980","title":"Enhancing Advanced Visual Reasoning Ability of Large Language Models","created":"2024-09-21","cited_by_count":18,"area":"lr"},{"id":"2402.11281","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","created":"2024-02-17","cited_by_count":17,"area":"mllm"},{"id":"2404.19509","title":"Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom","created":"2024-04-30","cited_by_count":15,"area":null},{"id":"2410.13854","title":"Can MLLMs Understand the Deep Implication Behind Chinese Images?","created":"2024-10-17","cited_by_count":14,"area":"mllm"},{"id":"2404.02415","title":"What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases","created":"2024-04-03","cited_by_count":13,"area":"mllm"},{"id":"2212.11214","title":"Crowd Score: A Method for the Evaluation of Jokes using Large Language Model AI Voters as Judges","created":"2022-12-21","cited_by_count":12,"area":null},{"id":"2402.12255","title":"Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2407.03000","title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values","created":"2024-07-03","cited_by_count":12,"area":"mllm"},{"id":"2502.20356","title":"Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs","created":"2025-02-27","cited_by_count":12,"area":"alignment"},{"id":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2405.19088","title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","created":"2024-05-29","cited_by_count":11,"area":"mllm"},{"id":"2406.10318","title":"Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding","created":"2024-06-14","cited_by_count":11,"area":"mllm"},{"id":"2502.08946","title":"The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2407.19474","title":"Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models","created":"2024-07-28","cited_by_count":10,"area":null},{"id":"2501.15147","title":"A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models","created":"2025-01-25","cited_by_count":10,"area":"lr"},{"id":"2307.11636","title":"OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2403.00794","title":"Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2409.13592","title":"YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models","created":"2024-09-20","cited_by_count":9,"area":"mllm"},{"id":"2405.07280","title":"Humor Mechanics: Advancing Humor Generation with Multistep Reasoning","created":"2024-05-12","cited_by_count":8,"area":null},{"id":"2407.10735","title":"Transforming Agency. On the mode of existence of Large Language Models","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2410.13088","title":"Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models","created":"2024-10-16","cited_by_count":7,"area":"mllm"},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2508.11011","title":"Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?","created":"2025-08-14","cited_by_count":7,"area":"mllm"},{"id":"2606.00820","title":"Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate","created":"2026-05-30","cited_by_count":7,"area":"lr"},{"id":"2406.13564","title":"HumorDB: Can AI understand graphical humor?","created":"2024-06-19","cited_by_count":6,"area":"mllm"},{"id":"2410.10112","title":"Can We Predict Performance of Large Models across Vision-Language Tasks?","created":"2024-10-14","cited_by_count":6,"area":"mllm"},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2504.13120","title":"Probing and Inducing Combinational Creativity in Vision-Language Models","created":"2025-04-17","cited_by_count":6,"area":"mllm"},{"id":"2507.13335","title":"Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2510.00567","title":"Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2311.09130","title":"Social Meme-ing: Measuring Linguistic Variation in Memes","created":"2023-11-15","cited_by_count":5,"area":null},{"id":"2411.14137","title":"VAGUE: Visual Contexts Clarify Ambiguous Expressions","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2412.11906","title":"PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2503.03651","title":"DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles","created":"2025-03-05","cited_by_count":5,"area":null},{"id":"2505.17019","title":"Let Androids Dream of Electric Sheep: A Human-Inspired Image Implication Understanding and Reasoning Framework","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2509.12248","title":"Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics","created":"2025-09-12","cited_by_count":5,"area":"mllm"},{"id":"2509.21175","title":"Who's Laughing Now? An Overview of Computational Humour Generation and Explanation","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2502.13925","title":"Beyond Single Frames: Can LMMs Comprehend Temporal and Contextual Narratives in Image Sequences?","created":"2025-02-19","cited_by_count":4,"area":"mllm"},{"id":"2505.09825","title":"KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning","created":"2025-05-14","cited_by_count":4,"area":"lr"},{"id":"2512.15653","title":"Characterizing Mamba's Selective Memory using Auto-Encoders","created":"2025-12-17","cited_by_count":4,"area":"ssm"},{"id":"2601.09692","title":"Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2411.10761","title":"Can Generic LLMs Help Analyze Child-adult Interactions Involving Children with Autism in Clinical Observation?","created":"2024-11-16","cited_by_count":3,"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":"2606.23196","title":"When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2405.15818","title":"DuanzAI: Slang-Enhanced LLM with Prompt for Humor Understanding","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2406.04470","title":"DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks","created":"2024-06-06","cited_by_count":2,"area":"mllm"},{"id":"2504.02983","title":"Hummus: A Dataset of Humorous Multimodal Metaphor Use","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2511.22805","title":"From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images","created":"2025-11-27","cited_by_count":2,"area":"mllm"},{"id":"2603.23229","title":"I Came, I Saw, I Explained: Benchmarking Multimodal LLMs on Figurative Meaning in Memes","created":"2026-03-24","cited_by_count":2,"area":"mllm"},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2407.18949","title":"Predicting Winning Captions for Weekly New Yorker Comics","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2409.01037","title":"NYK-MS: A Well-annotated Multi-modal Metaphor and Sarcasm Understanding Benchmark on Cartoon-Caption Dataset","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2501.16635","title":"Why Do We Laugh? Annotation and Taxonomy Generation for Laughable Contexts in Spontaneous Text Conversation","created":"2025-01-28","cited_by_count":1,"area":null},{"id":"2503.22093","title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark","created":"2025-03-28","cited_by_count":1,"area":"lr"},{"id":"2504.06577","title":"Bypassing Safety Guardrails in LLMs Using Humor","created":"2025-04-09","cited_by_count":1,"area":"safety"},{"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":"2510.01030","title":"Uncovering the Computational Ingredients of Human-Like Representations in LLMs","created":"2025-10-01","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":"2512.24555","title":"From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme","created":"2025-12-31","cited_by_count":1,"area":"lr"},{"id":"2602.10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.08757","title":"Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models","created":"2026-04-09","cited_by_count":1,"area":"alignment"},{"id":"2606.27378","title":"Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2410.21069","title":"EMOCPD: Efficient Attention-based Models for Computational Protein Design Using Amino Acid Microenvironment","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2509.25568","title":"Probing the Limits of Stylistic Alignment in Vision-Language Models","created":"2025-09-29","cited_by_count":0,"area":"mllm"},{"id":"2510.27196","title":"MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models","created":"2025-10-31","cited_by_count":0,"area":"mllm"},{"id":"2601.20451","title":"MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues","created":"2026-01-28","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":"2605.27832","title":"Playing with Words, Improving with Rewards: Training Language Models for Creative Association","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.01152","title":"AGC-Bench: Measuring Artificial General Creativity","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.10628","title":"Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.13189","title":"RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar","created":"2026-07-14","cited_by_count":0,"area":"agents"},{"id":"2607.19011","title":"Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2607.24082","title":"Towards High-Level Semantic Intelligence","created":"2026-07-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}