{"total":96,"rows":[{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77,"area":"mllm"},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"id":"2403.02910","title":"ImgTrojan: Jailbreaking Vision-Language Models with ONE Image","created":"2024-03-05","cited_by_count":57,"area":"mllm"},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","cited_by_count":19,"area":"mllm"},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2311.18237","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2409.05929","title":"M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture","created":"2024-09-09","cited_by_count":13,"area":"moe"},{"id":"2501.00958","title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","created":"2025-01-01","cited_by_count":9,"area":"mllm"},{"id":"2502.15682","title":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","created":"2025-02-21","cited_by_count":9,"area":null},{"id":"2504.06553","title":"ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2404.08535","title":"Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking","created":"2024-04-12","cited_by_count":7,"area":null},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2503.17080","title":"Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2505.01386","title":"CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2509.25638","title":"Generalized Contrastive Learning for Universal Multimodal Retrieval","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7,"area":"wm"},{"id":"2405.14294","title":"Tuning-free Universally-Supervised Semantic Segmentation","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2505.20229","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","created":"2025-05-26","cited_by_count":6,"area":"mechinterp"},{"id":"2506.01950","title":"DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2405.01028","title":"Technical Report of NICE Challenge at CVPR 2024: Caption Re-ranking Evaluation Using Ensembled CLIP and Consensus Scores","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2408.17057","title":"LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model","created":"2024-08-30","cited_by_count":5,"area":null},{"id":"2412.04434","title":"Towards Real-Time Open-Vocabulary Video Instance Segmentation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2509.14977","title":"EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence","created":"2025-09-18","cited_by_count":5,"area":"mllm"},{"id":"2605.08195","title":"ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device","created":"2026-05-05","cited_by_count":5,"area":null},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2409.14122","title":"Efficient and Effective Model Extraction","created":"2024-09-21","cited_by_count":4,"area":null},{"id":"2410.17243","title":"Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2412.20646","title":"Enhancing Visual Representation for Text-based Person Searching","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2505.23759","title":"Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint","created":"2025-05-29","cited_by_count":3,"area":"mllm"},{"id":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2509.21153","title":"WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2511.08417","title":"NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2603.07022","title":"OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2506.19955","title":"ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.10510","title":"Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2508.01074","title":"Evading Data Provenance in Deep Neural Networks","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2509.08003","title":"An Explainable Deep Neural Network with Frequency-Aware Channel and Spatial Refinement for Flood Prediction in Sustainable Cities","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2602.12173","title":"SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2503.07603","title":"Should VLMs be Pre-trained with Image Data?","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2503.17110","title":"Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2504.07567","title":"Benchmarking Image Embeddings for E-Commerce: Evaluating Off-the Shelf Foundation Models, Fine-Tuning Strategies and Practical Trade-offs","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2505.06699","title":"Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws","created":"2025-05-10","cited_by_count":1,"area":null},{"id":"2505.07675","title":"Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization","created":"2025-05-12","cited_by_count":1,"area":"mllm"},{"id":"2505.18053","title":"FDBPL: Faster Distillation-Based Prompt Learning for Region-Aware Vision-Language Models Adaptation","created":"2025-05-23","cited_by_count":1,"area":"mllm"},{"id":"2602.07849","title":"LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge","created":"2026-02-08","cited_by_count":1,"area":"mllm"},{"id":"2604.01179","title":"A ROS 2 Wrapper for Florence-2: Multi-Mode Local Vision-Language Inference for Robotic Systems","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2606.24253","title":"TuringViT: Making SOTA Vision Transformers Accessible to All","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2410.10879","title":"Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency","created":"2024-10-09","cited_by_count":0,"area":"mllm"},{"id":"2412.03871","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","created":"2024-12-05","cited_by_count":0,"area":"mllm"},{"id":"2503.21069","title":"Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing","created":"2025-03-27","cited_by_count":0,"area":"diffusion"},{"id":"2504.13590","title":"HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2505.02746","title":"Using Knowledge Graphs to harvest datasets for efficient CLIP model training","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2506.00910","title":"PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models","created":"2025-06-01","cited_by_count":0,"area":"mllm"},{"id":"2506.19288","title":"Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding","created":"2025-06-24","cited_by_count":0,"area":"mllm"},{"id":"2508.04028","title":"Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval","created":"2025-08-06","cited_by_count":0,"area":"mllm"},{"id":"2508.13713","title":"Hierarchical Vision-Language Retrieval of Educational Metaverse Content in Agriculture","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2510.02869","title":"Representing Beauty: Towards a Participatory but Objective Latent Aesthetics","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.19559","title":"A Matter of Time: Revealing the Structure of Time in Vision-Language Models","created":"2025-10-22","cited_by_count":0,"area":"mllm"},{"id":"2511.17886","title":"When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA","created":"2025-11-22","cited_by_count":0,"area":"mllm"},{"id":"2602.05909","title":"CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.12641","title":"Artic: AI-oriented Real-time Communication for MLLM Video Assistant","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.12659","title":"IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models","created":"2026-02-13","cited_by_count":0,"area":"mllm"},{"id":"2602.12748","title":"X-SYS: A Reference Architecture for Interactive Explanation Systems","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.00136","title":"TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings","created":"2026-02-24","cited_by_count":0,"area":"mllm"},{"id":"2603.05421","title":"DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression","created":"2026-03-05","cited_by_count":0,"area":"mllm"},{"id":"2603.29631","title":"Storing Less, Finding More: How Novelty Filtering Improves Cross-Modal Retrieval on Edge Cameras","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.15622","title":"AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.19054","title":"Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.10190","title":"DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.18029","title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.23274","title":"U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.27893","title":"SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.12849","title":"SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.17650","title":"MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block","created":"2026-06-16","cited_by_count":0,"area":"ssm"},{"id":"2607.02371","title":"VisionAId: An Offline-First Multimodal Android Assistant for People with Visual Impairment, Featuring Personalized Object Retrieval","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.28211","title":"Scaling Vision-Language Models Is Not Enough to Mitigate Bias","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.04423","title":"Foreseeing the Invisible: Amodal Reconstruction of Leaf Fossil Images","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.04604","title":"COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06170","title":"Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.24935","title":"A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.29364","title":"Sketch2Inspire: Structure-Sensitive Evaluation for Product Retrieval","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.05782","title":"Distilling Vision-Language Models for On-Device Fire Understanding","created":"2026-09-05","cited_by_count":0,"area":"mllm"},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16946","title":"High-Fidelity Video Quality Assessment with VQA-Specific Saliency","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.31135","title":"Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}