{"list":"other","total":67,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255},{"id":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209},{"id":"2104.08223","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","created":"2021-04-16","cited_by_count":190},{"id":"1807.10550","title":"X2Face: A network for controlling face generation by using images, audio, and pose codes","created":"2018-07-27","cited_by_count":189},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151},{"id":"1906.06337","title":"Realistic Speech-Driven Facial Animation with GANs","created":"2019-06-14","cited_by_count":142},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81},{"id":"2310.00434","title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","created":"2023-09-30","cited_by_count":81},{"id":"2301.00023","title":"Imitator: Personalized Speech-driven 3D Facial Animation","created":"2022-12-30","cited_by_count":74},{"id":"2203.13508","title":"BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis","created":"2022-03-25","cited_by_count":64},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59},{"id":"2111.00203","title":"Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis","created":"2021-10-30","cited_by_count":56},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55},{"id":"2312.08459","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","created":"2023-12-13","cited_by_count":55},{"id":"2211.09809","title":"SPACE: Speech-driven Portrait Animation with Controllable Expression","created":"2022-11-17","cited_by_count":49},{"id":"1903.12020","title":"Describing like humans: on diversity in image captioning","created":"2019-03-28","cited_by_count":46},{"id":"2008.05023","title":"Audio- and Gaze-driven Facial Animation of Codec Avatars","created":"2020-08-11","cited_by_count":46},{"id":"2205.01155","title":"Emotion-Controllable Generalized Talking Face Generation","created":"2022-05-02","cited_by_count":43},{"id":"2210.12315","title":"Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model","created":"2022-10-22","cited_by_count":41},{"id":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40},{"id":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37},{"id":"2212.04970","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","created":"2022-12-09","cited_by_count":33},{"id":"2312.10381","title":"SECap: Speech Emotion Captioning with Large Language Model","created":"2023-12-16","cited_by_count":33},{"id":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32},{"id":"1806.00154","title":"Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks","created":"2018-06-01","cited_by_count":21},{"id":"2311.17465","title":"AgentAvatar: Disentangling Planning, Driving and Rendering for Photorealistic Avatar Agents","created":"2023-11-29","cited_by_count":11},{"id":"2110.04425","title":"Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset","created":"2021-10-09","cited_by_count":10},{"id":"2306.07579","title":"Parametric Implicit Face Representation for Audio-Driven Facial Reenactment","created":"2023-06-13","cited_by_count":7}],"next_cursor":null}