{"list":"other","total":61,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372},{"id":"2406.15252","title":"VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation","created":"2024-06-21","cited_by_count":197},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"2004.15011","title":"TLDR: Extreme Summarization of Scientific Documents","created":"2020-04-30","cited_by_count":136},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"2104.07606","title":"Planning with Learned Entity Prompts for Abstractive Summarization","created":"2021-04-15","cited_by_count":75},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65},{"id":"2312.10300","title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","created":"2023-12-16","cited_by_count":54},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53},{"id":"2306.07799","title":"ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer","created":"2023-06-13","cited_by_count":50},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46},{"id":"2010.05406","title":"VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles","created":"2020-10-12","cited_by_count":44},{"id":"2207.00397","title":"Conditional Generation with a Question-Answering Blueprint","created":"2022-07-01","cited_by_count":44},{"id":"2310.08475","title":"Can We Edit Multimodal Large Language Models?","created":"2023-10-12","cited_by_count":44},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41},{"id":"2109.07446","title":"When Does Translation Require Context? A Data-driven, Multilingual Exploration","created":"2021-09-15","cited_by_count":36},{"id":"2109.13070","title":"Controllable Neural Dialogue Summarization with Personal Named Entity Planning","created":"2021-09-27","cited_by_count":36},{"id":"2402.03746","title":"Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback","created":"2024-02-06","cited_by_count":36},{"id":"2012.07808","title":"Unsupervised Opinion Summarization with Content Planning","created":"2020-12-14","cited_by_count":27},{"id":"1807.09418","title":"Video Storytelling: Textual Summaries for Events","created":"2018-07-25","cited_by_count":22},{"id":"1906.01351","title":"TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks","created":"2019-06-04","cited_by_count":20},{"id":"2403.05303","title":"ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications","created":"2024-03-08","cited_by_count":20},{"id":"2006.02286","title":"Learning Kernel Tests Without Data Splitting","created":"2020-06-03","cited_by_count":19},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19},{"id":"2310.14520","title":"QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing","created":"2023-10-23","cited_by_count":19},{"id":"2305.16784","title":"Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization","created":"2023-05-26","cited_by_count":17},{"id":"2109.05160","title":"StreamHover: Livestream Transcript Summarization and Annotation","created":"2021-09-11","cited_by_count":15},{"id":"2305.10387","title":"Elaborative Simplification as Implicit Questions Under Discussion","created":"2023-05-17","cited_by_count":14},{"id":"2110.01280","title":"Leveraging Information Bottleneck for Scientific Document Summarization","created":"2021-10-04","cited_by_count":13},{"id":"2403.03823","title":"A Modular Approach for Multimodal Summarization of TV Shows","created":"2024-03-06","cited_by_count":13},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12},{"id":"2403.17768","title":"SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation","created":"2024-03-26","cited_by_count":12},{"id":"2405.00657","title":"RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization","created":"2024-05-01","cited_by_count":11},{"id":"2409.14907","title":"Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization","created":"2024-09-23","cited_by_count":11},{"id":"2310.14503","title":"Diversify Question Generation with Retrieval-Augmented Style Transfer","created":"2023-10-23","cited_by_count":10},{"id":"2305.14205","title":"$\\mu$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge","created":"2023-05-23","cited_by_count":7},{"id":"2310.05295","title":"Visual Storytelling with Question-Answer Plans","created":"2023-10-08","cited_by_count":5},{"id":"2408.01046","title":"QUDSELECT: Selective Decoding for Questions Under Discussion Parsing","created":"2024-08-02","cited_by_count":5},{"id":"2206.00847","title":"TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary Generation","created":"2022-06-02","cited_by_count":4},{"id":"2411.03531","title":"Personalized Video Summarization by Multimodal Video Understanding","created":"2024-11-05","cited_by_count":3},{"id":"2312.08282","title":"Prompting LLMs with content plans to enhance the summarization of scientific articles","created":"2023-12-13","cited_by_count":2}],"next_cursor":null}