{"total":712,"rows":[{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361,"area":"diffusion"},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290,"area":null},{"id":"2311.07575","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","created":"2023-11-13","cited_by_count":286,"area":"mllm"},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169,"area":null},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163,"area":"diffusion"},{"id":"2408.00874","title":"Medical SAM 2: Segment medical images as video via Segment Anything Model 2","created":"2024-08-01","cited_by_count":154,"area":null},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141,"area":"ssm"},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139,"area":"mllm"},{"id":"2602.04770","title":"Generative Modeling via Drifting","created":"2026-02-04","cited_by_count":116,"area":null},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113,"area":"agents"},{"id":"2406.04339","title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","created":"2024-06-06","cited_by_count":103,"area":"vla"},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95,"area":"diffusion"},{"id":"2401.02384","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","created":"2024-01-04","cited_by_count":79,"area":"mllm"},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"id":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77,"area":null},{"id":"2505.04769","title":"Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges","created":"2025-05-07","cited_by_count":74,"area":"mllm"},{"id":"2506.24044","title":"A Survey on Vision-Language-Action Models for Autonomous Driving","created":"2025-06-30","cited_by_count":72,"area":"mllm"},{"id":"2402.18848","title":"SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting","created":"2024-02-29","cited_by_count":67,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2411.16061","title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","created":"2024-11-25","cited_by_count":59,"area":null},{"id":"2601.22158","title":"One-step Latent-free Image Generation with Pixel Mean Flows","created":"2026-01-29","cited_by_count":53,"area":null},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49,"area":null},{"id":"2404.09692","title":"XoFTR: Cross-modal Feature Matching Transformer","created":"2024-04-15","cited_by_count":48,"area":null},{"id":"2407.03653","title":"reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis","created":"2024-07-04","cited_by_count":48,"area":null},{"id":"2308.16258","title":"Robust Principles: Architectural Design Principles for Adversarially Robust CNNs","created":"2023-08-30","cited_by_count":46,"area":null},{"id":"2401.05224","title":"Do Vision and Language Encoders Represent the World Similarly?","created":"2024-01-10","cited_by_count":44,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"id":"2312.07330","title":"Learned representation-guided diffusion models for large-image generation","created":"2023-12-12","cited_by_count":40,"area":"diffusion"},{"id":"2511.03334","title":"UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions","created":"2025-11-05","cited_by_count":38,"area":null},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37,"area":null},{"id":"2410.23132","title":"Revisiting MAE pre-training for 3D medical image segmentation","created":"2024-10-30","cited_by_count":35,"area":null},{"id":"2505.18032","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2402.04362","title":"Neural Networks Learn Statistics of Increasing Complexity","created":"2024-02-06","cited_by_count":31,"area":null},{"id":"2506.13053","title":"ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching","created":"2025-06-16","cited_by_count":30,"area":"diffusion"},{"id":"2404.11313","title":"NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results","created":"2024-04-17","cited_by_count":29,"area":null},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29,"area":null},{"id":"2403.05061","title":"RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features","created":"2024-03-08","cited_by_count":28,"area":"distill"},{"id":"2402.12365","title":"Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators","created":"2024-02-19","cited_by_count":27,"area":null},{"id":"2407.20174","title":"Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning","created":"2024-07-29","cited_by_count":27,"area":"mllm"},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2405.19366","title":"ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text","created":"2024-05-26","cited_by_count":26,"area":null},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25,"area":null},{"id":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25,"area":null},{"id":"2401.17221","title":"MouSi: Poly-Visual-Expert Vision-Language Models","created":"2024-01-30","cited_by_count":24,"area":"mllm"},{"id":"2411.15858","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","created":"2024-11-24","cited_by_count":24,"area":null},{"id":"2412.04077","title":"SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning","created":"2024-12-05","cited_by_count":24,"area":null},{"id":"2305.12972","title":"VanillaNet: the Power of Minimalism in Deep Learning","created":"2023-05-22","cited_by_count":23,"area":null},{"id":"2408.05945","title":"MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection","created":"2024-08-12","cited_by_count":23,"area":null},{"id":"2412.06602","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2412.13840","title":"Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey","created":"2024-12-18","cited_by_count":23,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2410.09132","title":"When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning","created":"2024-10-11","cited_by_count":22,"area":null},{"id":"2302.08210","title":"A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold","created":"2023-02-16","cited_by_count":21,"area":null},{"id":"2306.05658","title":"GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment","created":"2023-06-09","cited_by_count":21,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2407.04616","title":"Isomorphic Pruning for Vision Models","created":"2024-07-05","cited_by_count":21,"area":null},{"id":"2402.19082","title":"VideoMAC: Video Masked Autoencoders Meet ConvNets","created":"2024-02-29","cited_by_count":20,"area":null},{"id":"2404.16687","title":"NTIRE 2024 Quality Assessment of AI-Generated Content Challenge","created":"2024-04-25","cited_by_count":20,"area":null},{"id":"2405.17871","title":"Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment","created":"2024-05-28","cited_by_count":20,"area":"mllm"},{"id":"2506.07902","title":"FunDiff: Diffusion Models over Function Spaces for Physics-Informed Generative Modeling","created":"2025-06-09","cited_by_count":20,"area":"diffusion"},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2412.00965","title":"Token Cropr: Faster ViTs for Quite a Few Tasks","created":"2024-12-01","cited_by_count":19,"area":"inference"},{"id":"2503.22081","title":"A Survey on Remote Sensing Foundation Models: From Vision to Multimodality","created":"2025-03-28","cited_by_count":19,"area":null},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"area":"ssm"},{"id":"2505.19476","title":"FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching","created":"2025-05-26","cited_by_count":17,"area":"diffusion"},{"id":"2509.24791","title":"Vision Function Layer in Multimodal LLMs","created":"2025-09-29","cited_by_count":17,"area":"mllm"},{"id":"2304.13089","title":"Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations","created":"2023-04-25","cited_by_count":16,"area":null},{"id":"2402.02263","title":"MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers","created":"2024-02-03","cited_by_count":16,"area":null},{"id":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2501.04670","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"id":"2402.01204","title":"A Survey on Self-Supervised Learning for Non-Sequential Tabular Data","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2407.13772","title":"GroupMamba: Efficient Group-Based Visual State Space Model","created":"2024-07-18","cited_by_count":15,"area":"ssm"},{"id":"2512.16874","title":"Pixel Seal: Adversarial-only training for invisible image and video watermarking","created":"2025-12-18","cited_by_count":15,"area":null},{"id":"2303.08557","title":"Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey","created":"2023-03-15","cited_by_count":14,"area":null},{"id":"2410.17241","title":"Frontiers in Intelligent Colonoscopy","created":"2024-10-22","cited_by_count":14,"area":null},{"id":"2502.18290","title":"Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models","created":"2025-02-25","cited_by_count":14,"area":"mllm"},{"id":"2503.03437","title":"JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba","created":"2025-03-05","cited_by_count":14,"area":"ssm"},{"id":"2511.20030","title":"Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering","created":"2025-11-25","cited_by_count":14,"area":null},{"id":"2306.01904","title":"Overcoming the Stability Gap in Continual Learning","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2306.05411","title":"R-MAE: Regions Meet Masked Autoencoders","created":"2023-06-08","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2405.15018","title":"What Variables Affect Out-of-Distribution Generalization in Pretrained Models?","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2504.12186","title":"CoMotion: Concurrent Multi-person 3D Motion","created":"2025-04-16","cited_by_count":13,"area":null},{"id":"2509.20234","title":"ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2602.05576","title":"OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph","created":"2026-02-05","cited_by_count":13,"area":null},{"id":"2302.05666","title":"Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels","created":"2023-02-11","cited_by_count":12,"area":"distill"},{"id":"2304.07051","title":"The Second Monocular Depth Estimation Challenge","created":"2023-04-14","cited_by_count":12,"area":null}],"next_cursor":"100"}