{"list":"other","total":56,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2005.03545","title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","created":"2020-05-07","cited_by_count":265},{"id":"1702.01992","title":"Gated Multimodal Units for Information Fusion","created":"2017-02-07","cited_by_count":248},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186},{"id":"2102.04830","title":"Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis","created":"2021-02-09","cited_by_count":180},{"id":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153},{"id":"1812.07809","title":"Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities","created":"2018-12-19","cited_by_count":149},{"id":"2109.00412","title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","created":"2021-09-01","cited_by_count":131},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"2202.05306","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","created":"2022-02-10","cited_by_count":95},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53},{"id":"2003.13962","title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text","created":"2020-03-31","cited_by_count":46},{"id":"2209.02604","title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","created":"2022-08-22","cited_by_count":44},{"id":"1902.10547","title":"An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models","created":"2019-02-27","cited_by_count":39},{"id":"2205.02455","title":"COGMEN: COntextualized GNN based Multimodal Emotion recognitioN","created":"2022-05-05","cited_by_count":29},{"id":"2310.05804","title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis","created":"2023-10-09","cited_by_count":29},{"id":"1908.06938","title":"Encoder-Agnostic Adaptation for Conditional Language Generation","created":"2019-08-19","cited_by_count":27},{"id":"2401.03429","title":"MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition","created":"2024-01-07","cited_by_count":27},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22},{"id":"2203.12441","title":"M-SENA: An Integrated Platform for Multimodal Sentiment Analysis","created":"2022-03-23","cited_by_count":21},{"id":"1805.08660","title":"Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment","created":"2018-05-22","cited_by_count":20},{"id":"2205.15465","title":"Analyzing Modality Robustness in Multimodal Sentiment Analysis","created":"2022-05-30","cited_by_count":20},{"id":"2212.14453","title":"Learning Multimodal Data Augmentation in Feature Space","created":"2022-12-29","cited_by_count":18},{"id":"2401.13388","title":"UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion","created":"2024-01-24","cited_by_count":15},{"id":"1707.09538","title":"Benchmarking Multimodal Sentiment Analysis","created":"2017-07-29","cited_by_count":11},{"id":"2201.09828","title":"MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis","created":"2022-01-24","cited_by_count":6},{"id":"2305.01954","title":"SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method","created":"2023-05-03","cited_by_count":3}],"next_cursor":null}