{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"1503.03535","title":"On Using Monolingual Corpora in Neural Machine Translation","created":"2015-03-11","cited_by_count":150},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140},{"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":"1712.01996","title":"An analysis of incorporating an external language model into a sequence-to-sequence model","created":"2017-12-06","cited_by_count":111},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"1612.02695","title":"Towards better decoding and language model integration in sequence to sequence models","created":"2016-12-08","cited_by_count":100},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91},{"id":"1708.06426","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","created":"2017-08-21","cited_by_count":88},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2309.15649","title":"Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting","created":"2023-09-27","cited_by_count":72},{"id":"1908.10992","title":"Two-Pass End-to-End Speech Recognition","created":"2019-08-29","cited_by_count":64},{"id":"2010.06572","title":"Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!","created":"2020-10-13","cited_by_count":62},{"id":"2003.07962","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","created":"2020-03-17","cited_by_count":57},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42},{"id":"2008.03822","title":"Distilling the Knowledge of BERT for Sequence-to-Sequence ASR","created":"2020-08-09","cited_by_count":41},{"id":"2102.07856","title":"Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification","created":"2021-02-15","cited_by_count":39},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39},{"id":"2202.01094","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","created":"2022-02-02","cited_by_count":34},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34},{"id":"2209.08928","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","created":"2022-09-19","cited_by_count":34},{"id":"2210.14567","title":"Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization","created":"2022-10-26","cited_by_count":29},{"id":"1812.02142","title":"End-to-end contextual speech recognition using class language models and a token passing decoder","created":"2018-12-05","cited_by_count":26},{"id":"2210.06175","title":"Exploring Efficient-tuning Methods in Self-supervised Speech Models","created":"2022-10-10","cited_by_count":26},{"id":"2212.05301","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","created":"2022-12-10","cited_by_count":22},{"id":"2011.11715","title":"Multi-task Language Modeling for Improving Speech Recognition of Rare Words","created":"2020-11-23","cited_by_count":21},{"id":"2309.16953","title":"Enhancing Code-switching Speech Recognition with Interactive Language Biases","created":"2023-09-29","cited_by_count":21},{"id":"2211.01317","title":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","created":"2022-11-02","cited_by_count":17},{"id":"2210.04468","title":"Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation","created":"2022-10-10","cited_by_count":13},{"id":"2307.13205","title":"Text-oriented Modality Reinforcement Network for Multimodal Sentiment Analysis from Unaligned Multimodal Sequences","created":"2023-07-25","cited_by_count":13},{"id":"2308.09694","title":"Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition","created":"2023-08-18","cited_by_count":13},{"id":"2306.01015","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","created":"2023-06-01","cited_by_count":10},{"id":"2212.01039","title":"SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition","created":"2022-12-02","cited_by_count":9},{"id":"2305.11244","title":"A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model","created":"2023-05-18","cited_by_count":8},{"id":"2310.13013","title":"Generative error correction for code-switching speech recognition using large language models","created":"2023-10-17","cited_by_count":7},{"id":"2204.04288","title":"Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction","created":"2022-04-08","cited_by_count":5}],"next_cursor":null}