{"list":"other","total":54,"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268},{"id":"2411.10442","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","created":"2024-11-15","cited_by_count":239},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128},{"id":"2401.06775","title":"Large language models in healthcare and medical domain: A review","created":"2023-12-12","cited_by_count":127},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112},{"id":"2304.04339","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","created":"2023-04-10","cited_by_count":96},{"id":"2402.18659","title":"Large Language Models and Games: A Survey and Roadmap","created":"2024-02-28","cited_by_count":93},{"id":"2302.05981","title":"MarioGPT: Open-Ended Text2Level Generation through Large Language Models","created":"2023-02-12","cited_by_count":64},{"id":"2408.13296","title":"The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities","created":"2024-08-23","cited_by_count":64},{"id":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60},{"id":"2406.07765","title":"Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward","created":"2024-06-11","cited_by_count":45},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38},{"id":"2304.02868","title":"Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions","created":"2023-04-06","cited_by_count":30},{"id":"2308.13911","title":"A Wide Evaluation of ChatGPT on Affective Computing Tasks","created":"2023-08-26","cited_by_count":30},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25},{"id":"2309.01664","title":"Fine-grained Affective Processing Capabilities Emerging from Large Language Models","created":"2023-09-04","cited_by_count":24},{"id":"2308.07540","title":"CALYPSO: LLMs as Dungeon Masters' Assistants","created":"2023-08-15","cited_by_count":23},{"id":"2104.02643","title":"The Arousal video Game AnnotatIoN (AGAIN) Dataset","created":"2021-04-06","cited_by_count":18},{"id":"2307.00259","title":"InstructEval: Systematic Evaluation of Instruction Selection Methods","created":"2023-07-01","cited_by_count":13},{"id":"1907.01008","title":"PAGAN: Video Affect Annotation Made Easy","created":"2019-07-01","cited_by_count":12},{"id":"2106.10060","title":"Contrastive Learning of Generalized Game Representations","created":"2021-06-18","cited_by_count":11},{"id":"2110.00978","title":"Towards General Models of Player Experience: A Study Within Genres","created":"2021-10-03","cited_by_count":11},{"id":"2405.07229","title":"MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks","created":"2024-05-12","cited_by_count":11},{"id":"2403.17125","title":"The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition","created":"2024-03-25","cited_by_count":10},{"id":"2310.06136","title":"Predicting Player Engagement in Tom Clancy's The Division 2: A Multimodal Approach via Pixels and Gamepad Actions","created":"2023-10-09","cited_by_count":9},{"id":"2107.10552","title":"Privileged Information for Modeling Affect In The Wild","created":"2021-07-22","cited_by_count":8},{"id":"1902.00040","title":"Your Gameplay Says It All: Modelling Motivation in Tom Clancy's The Division","created":"2019-01-31","cited_by_count":7},{"id":"2008.07207","title":"Moment-to-moment Engagement Prediction through the Eyes of the Observer: PUBG Streaming on Twitch","created":"2020-08-17","cited_by_count":5},{"id":"2402.01335","title":"BehAVE: Behaviour Alignment of Video Game Encodings","created":"2024-02-02","cited_by_count":5},{"id":"2404.04234","title":"player2vec: A Language Modeling Approach to Understand Player Behavior in Games","created":"2024-04-05","cited_by_count":5},{"id":"2407.12787","title":"GameVibe: A Multimodal Affective Game Corpus","created":"2024-06-17","cited_by_count":5},{"id":"2409.13002","title":"Across-Game Engagement Modelling via Few-Shot Learning","created":"2024-09-19","cited_by_count":4},{"id":"2408.04420","title":"Recognizing Emotion Regulation Strategies from Human Behavior with Large Language Models","created":"2024-08-08","cited_by_count":3}],"next_cursor":null}