{"list":"other","total":75,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186},{"id":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2406.07209","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","created":"2024-06-11","cited_by_count":144},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136},{"id":"2404.04650","title":"InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization","created":"2024-04-06","cited_by_count":123},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80},{"id":"2309.15664","title":"Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing","created":"2023-09-27","cited_by_count":76},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2305.03382","title":"Guided Image Synthesis via Initial Image Editing in Diffusion Model","created":"2023-05-05","cited_by_count":63},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53},{"id":"2107.13780","title":"Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation","created":"2021-07-29","cited_by_count":42},{"id":"2501.03931","title":"MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers","created":"2025-01-07","cited_by_count":34},{"id":"2507.03905","title":"EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation","created":"2025-07-05","cited_by_count":29},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28},{"id":"2501.12909","title":"FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces","created":"2025-01-22","cited_by_count":28},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22},{"id":"2511.23475","title":"AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement","created":"2025-11-28","cited_by_count":20},{"id":"2207.12817","title":"Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation","created":"2022-07-26","cited_by_count":19},{"id":"2403.04381","title":"Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation","created":"2024-03-07","cited_by_count":19},{"id":"2508.19320","title":"MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation","created":"2025-08-26","cited_by_count":19},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18},{"id":"2403.02090","title":"Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations","created":"2024-03-04","cited_by_count":18},{"id":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","cited_by_count":18},{"id":"2409.15316","title":"Towards Social AI: A Survey on Understanding Social Interactions","created":"2024-09-05","cited_by_count":16},{"id":"2312.12870","title":"The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective","created":"2023-12-20","cited_by_count":14},{"id":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13},{"id":"2507.12956","title":"FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers","created":"2025-07-17","cited_by_count":13},{"id":"2410.20974","title":"MovieCharacter: A Tuning-Free Framework for Controllable Character Video Synthesis","created":"2024-10-28","cited_by_count":12},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12},{"id":"2504.18039","title":"MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind","created":"2025-04-25","cited_by_count":12},{"id":"2504.02244","title":"SocialGesture: Delving into Multi-person Gesture Understanding","created":"2025-04-03","cited_by_count":11},{"id":"2512.09327","title":"UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking","created":"2025-12-10","cited_by_count":11},{"id":"2602.00607","title":"MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation","created":"2026-01-31","cited_by_count":11},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9},{"id":"2506.19833","title":"Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router","created":"2025-06-24","cited_by_count":6},{"id":"2511.16221","title":"Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions","created":"2025-11-20","cited_by_count":6},{"id":"2508.03034","title":"MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention","created":"2025-08-05","cited_by_count":5},{"id":"2512.19546","title":"ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars","created":"2025-12-22","cited_by_count":5},{"id":"2512.01340","title":"EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans","created":"2025-12-01","cited_by_count":4},{"id":"2505.24389","title":"Leadership Assessment in Pediatric Intensive Care Unit Team Training","created":"2025-05-30","cited_by_count":3},{"id":"2508.03144","title":"LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editing","created":"2025-08-05","cited_by_count":3},{"id":"2511.18127","title":"SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting","created":"2025-11-22","cited_by_count":1},{"id":"2603.14794","title":"Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling","created":"2026-03-16","cited_by_count":1},{"id":"2603.29162","title":"From Natural Alignment to Conditional Controllability in Multimodal Dialogue","created":"2026-03-31","cited_by_count":1}],"next_cursor":null}