{"total":57,"rows":[{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343,"area":"mllm"},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229,"area":null},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69,"area":"mllm"},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66,"area":null},{"id":"2410.13638","title":"Scaling Wearable Foundation Models","created":"2024-10-17","cited_by_count":63,"area":null},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"area":null},{"id":"2306.03435","title":"On the Role of Attention in Prompt-tuning","created":"2023-06-06","cited_by_count":50,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2111.15121","title":"Pyramid Adversarial Training Improves ViT Performance","created":"2021-11-30","cited_by_count":39,"area":null},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39,"area":null},{"id":"2306.05407","title":"SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding","created":"2023-06-08","cited_by_count":38,"area":null},{"id":"2309.01858","title":"Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations","created":"2023-09-04","cited_by_count":28,"area":null},{"id":"2402.02887","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","created":"2024-02-05","cited_by_count":28,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25,"area":null},{"id":"2407.19985","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","created":"2024-07-29","cited_by_count":25,"area":"moe"},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24,"area":null},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2308.12394","title":"Self-Supervised Learning for Endoscopic Video Analysis","created":"2023-08-23","cited_by_count":22,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20,"area":null},{"id":"2212.02400","title":"Location-Aware Self-Supervised Transformers for Semantic Segmentation","created":"2022-12-05","cited_by_count":20,"area":null},{"id":"2211.09019","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2408.03006","title":"Dual-path Collaborative Generation Network for Emotional Video Captioning","created":"2024-08-06","cited_by_count":14,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2403.10519","title":"Frozen Feature Augmentation for Few-Shot Image Classification","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2306.11729","title":"Dense Video Object Captioning from Disjoint Supervision","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2302.01327","title":"Dual PatchNorm","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2403.02041","title":"A Generative Approach for Wikipedia-Scale Visual Entity Recognition","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2207.03807","title":"Beyond Transfer Learning: Co-finetuning for Action Localisation","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2406.08332","title":"UDON: Universal Dynamic Online distillatioN for generic image representations","created":"2024-06-12","cited_by_count":8,"area":"distill"},{"id":"2407.06183","title":"Stepping on the Edge: Curvature Aware Learning Rate Tuners","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2306.04822","title":"Optimizing ViViT Training: Time and Memory Reduction for Action Recognition","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2303.16887","title":"Towards Understanding the Effect of Pretraining Label Granularity","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2209.07474","title":"On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2508.12137","title":"Infusing fine-grained visual knowledge to Vision-Language Models","created":"2025-08-16","cited_by_count":2,"area":"mllm"},{"id":"2509.22259","title":"Rotary Position Encodings for Graphs","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2302.02752","title":"Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2312.00950","title":"Improve Supervised Representation Learning with Masked Image Modeling","created":"2023-12-01","cited_by_count":1,"area":null},{"id":"2510.20994","title":"VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2603.06731","title":"PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2610.04147","title":"You May Be Running the Wrong Inception Crop","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}