{"list":"other","total":58,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"2303.17604","title":"Token Merging for Fast Stable Diffusion","created":"2023-03-30","cited_by_count":224},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2003.10751","title":"TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks","created":"2020-03-24","cited_by_count":141},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116},{"id":"2503.09648","title":"A Survey on Trustworthy LLM Agents: Threats and Countermeasures","created":"2025-03-12","cited_by_count":96},{"id":"1907.06099","title":"Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis","created":"2019-07-13","cited_by_count":76},{"id":"1402.3511","title":"A Clockwork RNN","created":"2014-02-14","cited_by_count":72},{"id":"2103.16327","title":"Temporal Memory Relation Network for Workflow Recognition from Surgical Video","created":"2021-03-30","cited_by_count":66},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61},{"id":"2206.11053","title":"Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer","created":"2022-06-22","cited_by_count":59},{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56},{"id":"2210.00586","title":"Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2","created":"2022-10-02","cited_by_count":55},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49},{"id":"2102.12218","title":"Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures","created":"2021-02-24","cited_by_count":42},{"id":"2407.12998","title":"Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks","created":"2024-07-17","cited_by_count":40},{"id":"2503.04392","title":"AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management","created":"2025-03-06","cited_by_count":38},{"id":"2104.07545","title":"Hierarchical Learning for Generation with Long Source Sequences","created":"2021-04-15","cited_by_count":32},{"id":"2408.03867","title":"Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition","created":"2024-08-07","cited_by_count":32},{"id":"2506.02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence","created":"2025-06-03","cited_by_count":31},{"id":"2410.15686","title":"NetSafe: Exploring the Topological Safety of Multi-agent Networks","created":"2024-10-21","cited_by_count":29},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25},{"id":"2408.14028","title":"SurGen: Text-Guided Diffusion Model for Surgical Video Generation","created":"2024-08-26","cited_by_count":20},{"id":"2407.19305","title":"GP-VLS: A general-purpose vision language model for surgery","created":"2024-07-27","cited_by_count":17},{"id":"2503.10265","title":"SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis","created":"2025-03-13","cited_by_count":15},{"id":"2503.02950","title":"LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications","created":"2025-03-04","cited_by_count":14},{"id":"2407.20214","title":"SANGRIA: Surgical Video Scene Graph Optimization for Surgical Workflow Prediction","created":"2024-07-29","cited_by_count":12},{"id":"2401.05012","title":"HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting","created":"2024-01-10","cited_by_count":8},{"id":"2404.00322","title":"Instrument-tissue Interaction Detection Framework for Surgical Video Understanding","created":"2024-03-30","cited_by_count":8},{"id":"2407.17361","title":"MuST: Multi-Scale Transformers for Surgical Phase Recognition","created":"2024-07-24","cited_by_count":8},{"id":"2410.07753","title":"Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models","created":"2024-10-10","cited_by_count":8},{"id":"2506.21287","title":"HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation","created":"2025-06-26","cited_by_count":8},{"id":"2407.09230","title":"Surgical Text-to-Image Generation","created":"2024-07-12","cited_by_count":6},{"id":"2409.19608","title":"Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model","created":"2024-09-29","cited_by_count":6},{"id":"2306.08859","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","created":"2023-06-15","cited_by_count":5},{"id":"2405.18687","title":"Advancing Household Robotics: Deep Interactive Reinforcement Learning for Efficient Training and Enhanced Performance","created":"2024-05-29","cited_by_count":4},{"id":"2410.01677","title":"Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia","created":"2024-10-02","cited_by_count":4},{"id":"2412.18849","title":"SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation","created":"2024-12-25","cited_by_count":4},{"id":"2407.14296","title":"Foundation Models for Autonomous Robots in Unstructured Environments","created":"2024-07-19","cited_by_count":3},{"id":"2110.07404","title":"Socially assistive robots' deployment in healthcare settings: a global perspective","created":"2021-10-14","cited_by_count":2},{"id":"2405.02571","title":"ViTALS: Vision Transformer for Action Localization in Surgical Nephrectomy","created":"2024-05-04","cited_by_count":2},{"id":"2406.14576","title":"Towards Intelligent Speech Assistants in Operating Rooms: A Multimodal Model for Surgical Workflow Analysis","created":"2024-06-17","cited_by_count":2}],"next_cursor":null}