{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"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":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147},{"id":"2203.07190","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","created":"2022-03-14","cited_by_count":113},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2210.07688","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","created":"2022-10-14","cited_by_count":72},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61},{"id":"2403.08350","title":"CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model","created":"2024-03-13","cited_by_count":61},{"id":"2203.00386","title":"CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP","created":"2022-03-01","cited_by_count":60},{"id":"2109.04014","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","created":"2021-09-09","cited_by_count":50},{"id":"2405.00740","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","created":"2024-04-30","cited_by_count":42},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37},{"id":"2407.21794","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey","created":"2024-07-31","cited_by_count":36},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35},{"id":"2401.09181","title":"Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer","created":"2024-01-17","cited_by_count":31},{"id":"1909.02201","title":"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach","created":"2019-09-05","cited_by_count":30},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25},{"id":"2109.12487","title":"Parallel Refinements for Lexically Constrained Text Generation with BART","created":"2021-09-26","cited_by_count":24},{"id":"2403.04735","title":"SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM","created":"2024-03-07","cited_by_count":18},{"id":"2006.13611","title":"Recurrent Relational Memory Network for Unsupervised Image Captioning","created":"2020-06-24","cited_by_count":16},{"id":"1712.00733","title":"Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks","created":"2017-12-03","cited_by_count":12},{"id":"2304.13273","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","created":"2023-04-26","cited_by_count":11},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11},{"id":"2211.07275","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment","created":"2022-11-14","cited_by_count":8},{"id":"2312.02226","title":"Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition","created":"2023-12-04","cited_by_count":8},{"id":"2405.10311","title":"UniRAG: Universal Retrieval Augmentation for Large Vision Language Models","created":"2024-05-16","cited_by_count":8},{"id":"2309.08922","title":"Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models","created":"2023-09-16","cited_by_count":6},{"id":"2310.15324","title":"Videoprompter: an ensemble of foundational models for zero-shot video understanding","created":"2023-10-23","cited_by_count":5},{"id":"2311.09612","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","created":"2023-11-16","cited_by_count":5},{"id":"2307.02682","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","created":"2023-07-05","cited_by_count":4},{"id":"2404.00419","title":"Do Vision-Language Models Understand Compound Nouns?","created":"2024-03-30","cited_by_count":4},{"id":"2309.10783","title":"Language as the Medium: Multimodal Video Classification through text only","created":"2023-09-19","cited_by_count":3},{"id":"2303.05122","title":"M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios","created":"2023-03-09","cited_by_count":2}],"next_cursor":null}