{"list":"other","total":59,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"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":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"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":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2506.17298","title":"Mercury: Ultra-Fast Language Models Based on Diffusion","created":"2025-06-17","cited_by_count":235},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2501.03895","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","created":"2025-01-07","cited_by_count":166},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156},{"id":"2412.00733","title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","created":"2024-12-01","cited_by_count":122},{"id":"2304.07060","title":"DCFace: Synthetic Face Generation with Dual Condition Diffusion Model","created":"2023-04-14","cited_by_count":116},{"id":"2403.11641","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","created":"2024-03-18","cited_by_count":101},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80},{"id":"2004.09584","title":"ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric","created":"2020-04-20","cited_by_count":79},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56},{"id":"2303.02490","title":"Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later","created":"2023-03-04","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":"2410.03017","title":"Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise","created":"2024-10-03","cited_by_count":50},{"id":"2301.06281","title":"DPE: Disentanglement of Pose and Expression for General Video Portrait Editing","created":"2023-01-16","cited_by_count":46},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40},{"id":"2403.09069","title":"Dyadic Interaction Modeling for Social Behavior Generation","created":"2024-03-14","cited_by_count":32},{"id":"2505.18096","title":"DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations","created":"2025-05-23","cited_by_count":32},{"id":"2203.07931","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","created":"2022-03-15","cited_by_count":30},{"id":"2405.10272","title":"Faces that Speak: Jointly Synthesising Talking Face and Speech from Text","created":"2024-05-16","cited_by_count":21},{"id":"2305.15748","title":"ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions","created":"2023-05-25","cited_by_count":17},{"id":"2401.05166","title":"REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge","created":"2024-01-10","cited_by_count":16},{"id":"2305.15270","title":"Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation","created":"2023-05-24","cited_by_count":11},{"id":"2504.04010","title":"DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion","created":"2025-04-05","cited_by_count":10},{"id":"2012.04882","title":"Emotional Conversation Generation with Heterogeneous Graph Neural Network","created":"2020-12-09","cited_by_count":9},{"id":"2403.08312","title":"StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses","created":"2024-03-13","cited_by_count":9},{"id":"2502.13133","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions","created":"2025-02-18","cited_by_count":9},{"id":"2504.02433","title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","created":"2025-04-03","cited_by_count":9},{"id":"2505.17223","title":"REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge","created":"2025-05-22","cited_by_count":9},{"id":"2412.00719","title":"Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation","created":"2024-12-01","cited_by_count":8},{"id":"2503.21144","title":"ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model","created":"2025-03-27","cited_by_count":8},{"id":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8},{"id":"2412.20148","title":"DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis","created":"2024-12-28","cited_by_count":7},{"id":"2306.16003","title":"Text-driven Talking Face Synthesis by Reprogramming Audio-driven Models","created":"2023-06-28","cited_by_count":6},{"id":"2402.13724","title":"Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters","created":"2024-02-21","cited_by_count":6},{"id":"2410.09865","title":"SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data","created":"2024-10-13","cited_by_count":6},{"id":"2510.04712","title":"ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model","created":"2025-10-06","cited_by_count":4},{"id":"2506.23552","title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","created":"2025-06-30","cited_by_count":3},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1}],"next_cursor":null}