{"list":"other","total":263,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1906.01815","title":"Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)","created":"2019-06-05","cited_by_count":174},{"id":"2604.14148","title":"Seedance 2.0: Advancing Video Generation for World Complexity","created":"2026-04-15","cited_by_count":160},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117},{"id":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98},{"id":"1805.06939","title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","created":"2018-05-17","cited_by_count":82},{"id":"2203.13947","title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","created":"2022-03-26","cited_by_count":80},{"id":"2406.16264","title":"One Thousand and One Pairs: A \"novel\" challenge for long-context language models","created":"2024-06-24","cited_by_count":80},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79},{"id":"2204.12632","title":"Testing the Ability of Language Models to Interpret Figurative Language","created":"2022-04-26","cited_by_count":67},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63},{"id":"1805.06533","title":"Modeling Naive Psychology of Characters in Simple Commonsense Stories","created":"2018-05-16","cited_by_count":60},{"id":"2410.02603","title":"Agents' Room: Narrative Generation through Multi-step Collaboration","created":"2024-10-03","cited_by_count":57},{"id":"1808.10399","title":"Modeling Empathy and Distress in Reaction to News Stories","created":"2018-08-30","cited_by_count":52},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52},{"id":"2404.13627","title":"NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding","created":"2024-04-21","cited_by_count":51},{"id":"2109.05438","title":"\"Let Your Characters Tell Their Story\": A Dataset for Character-Centric Narrative Understanding","created":"2021-09-12","cited_by_count":48},{"id":"2402.15813","title":"Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method","created":"2024-02-24","cited_by_count":48},{"id":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","cited_by_count":47},{"id":"2308.08088","title":"Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection","created":"2023-08-16","cited_by_count":47},{"id":"2312.15523","title":"The Persuasive Power of Large Language Models","created":"2023-12-24","cited_by_count":47},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46},{"id":"2403.18058","title":"COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning","created":"2024-03-26","cited_by_count":45},{"id":"2503.23512","title":"SCORE: Story Coherence and Retrieval Enhancement for AI Narratives","created":"2025-03-30","cited_by_count":42},{"id":"2305.10172","title":"Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations","created":"2023-05-17","cited_by_count":41},{"id":"2305.15041","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","created":"2023-05-24","cited_by_count":37},{"id":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34},{"id":"2203.06419","title":"When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues","created":"2022-03-12","cited_by_count":33},{"id":"2305.14724","title":"I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors","created":"2023-05-24","cited_by_count":31},{"id":"2203.14139","title":"Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages","created":"2022-03-26","cited_by_count":30},{"id":"2406.19643","title":"Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation","created":"2024-06-28","cited_by_count":29},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28},{"id":"1906.00274","title":"\"President Vows to Cut <Taxes> Hair\": Dataset and Analysis of Creative Text Editing for Humorous Headlines","created":"2019-06-01","cited_by_count":27},{"id":"2407.21315","title":"Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances","created":"2024-07-31","cited_by_count":27},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25},{"id":"2108.12960","title":"LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation","created":"2021-08-30","cited_by_count":24},{"id":"2311.04915","title":"Chain of Empathy: Enhancing Empathetic Response of Large Language Models Based on Psychotherapy Models","created":"2023-11-02","cited_by_count":24},{"id":"2506.10857","title":"VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos","created":"2025-06-12","cited_by_count":24},{"id":"2511.01689","title":"Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI","created":"2025-11-03","cited_by_count":24},{"id":"2511.08723","title":"ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction","created":"2025-11-11","cited_by_count":24},{"id":"2402.01679","title":"STICKERCONV: Generating Multimodal Empathetic Responses from Scratch","created":"2024-01-20","cited_by_count":22},{"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},{"id":"2412.08687","title":"VisionArena: 230K Real World User-VLM Conversations with Preference Labels","created":"2024-12-11","cited_by_count":22},{"id":"2512.01282","title":"Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning","created":"2025-12-01","cited_by_count":22},{"id":"2205.01825","title":"AmbiPun: Generating Humorous Puns with Ambiguous Context","created":"2022-05-04","cited_by_count":21},{"id":"2210.13513","title":"ExPUNations: Augmenting Puns with Keywords and Explanations","created":"2022-10-24","cited_by_count":21},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21},{"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},{"id":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21},{"id":"2508.09600","title":"OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialogue","created":"2025-08-13","cited_by_count":21},{"id":"2205.12698","title":"Empathic Conversations: A Multi-level Dataset of Contextualized Conversations","created":"2022-05-25","cited_by_count":20},{"id":"2401.12585","title":"SLANG: New Concept Comprehension of Large Language Models","created":"2024-01-23","cited_by_count":20},{"id":"2408.11319","title":"SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding","created":"2024-08-21","cited_by_count":20},{"id":"2508.10848","title":"Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning","created":"2025-08-14","cited_by_count":20},{"id":"2210.11715","title":"Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection","created":"2022-10-21","cited_by_count":19},{"id":"2306.16650","title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","created":"2023-06-29","cited_by_count":19},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19},{"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},{"id":"2412.04509","title":"Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection","created":"2024-12-04","cited_by_count":19},{"id":"2208.08845","title":"CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation","created":"2022-08-18","cited_by_count":18},{"id":"2311.09675","title":"Where Do People Tell Stories Online? Story Detection Across Online Communities","created":"2023-11-16","cited_by_count":17},{"id":"2402.11281","title":"Can Large Multimodal Models Uncover Deep Semantics Behind Images?","created":"2024-02-17","cited_by_count":17},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17},{"id":"2505.19028","title":"InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts","created":"2025-05-25","cited_by_count":17},{"id":"2210.03884","title":"Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness","created":"2022-10-08","cited_by_count":16},{"id":"2405.17633","title":"HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs","created":"2024-05-27","cited_by_count":16},{"id":"2406.05862","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models","created":"2024-06-09","cited_by_count":16},{"id":"2407.21491","title":"Generative Expressive Conversational Speech Synthesis","created":"2024-07-31","cited_by_count":16},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16},{"id":"2105.03280","title":"Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms","created":"2021-04-25","cited_by_count":15}],"next_cursor":"100"}