{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439},{"id":"1812.00564","title":"Split learning for health: Distributed deep learning without sharing raw patient data","created":"2018-12-03","cited_by_count":395},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"id":"2012.06337","title":"Privacy and Robustness in Federated Learning: Attacks and Defenses","created":"2020-12-07","cited_by_count":166},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115},{"id":"2403.05156","title":"On Protecting the Data Privacy of Large Language Models (LLMs): A Survey","created":"2024-03-08","cited_by_count":96},{"id":"2001.03569","title":"Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics","created":"2020-01-10","cited_by_count":80},{"id":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46},{"id":"2409.08481","title":"USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s","created":"2024-09-13","cited_by_count":37},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31},{"id":"2004.10043","title":"Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression","created":"2020-04-21","cited_by_count":28},{"id":"2403.11694","title":"Object Segmentation-Assisted Inter Prediction for Versatile Video Coding","created":"2024-03-18","cited_by_count":22},{"id":"2206.05650","title":"Preprocessing Enhanced Image Compression for Machine Vision","created":"2022-06-12","cited_by_count":18},{"id":"2503.12926","title":"Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference","created":"2025-03-17","cited_by_count":18},{"id":"2105.10089","title":"Latent-space scalability for multi-task collaborative intelligence","created":"2021-05-21","cited_by_count":17},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15},{"id":"2409.19660","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","created":"2024-09-29","cited_by_count":14},{"id":"2306.10681","title":"VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision","created":"2023-06-19","cited_by_count":13},{"id":"2306.16670","title":"End-to-End Learnable Multi-Scale Feature Compression for VCM","created":"2023-06-29","cited_by_count":13},{"id":"2405.14674","title":"Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond","created":"2024-05-23","cited_by_count":12},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12},{"id":"2412.04307","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","created":"2024-12-05","cited_by_count":12},{"id":"2406.14898","title":"Safely Learning with Private Data: A Federated Learning Framework for Large Language Model","created":"2024-06-21","cited_by_count":11},{"id":"2405.04044","title":"DMOFC: Discrimination Metric-Optimized Feature Compression","created":"2024-05-07","cited_by_count":7},{"id":"2506.16495","title":"DT-UFC: Universal Large Model Feature Coding via Peaky-to-Balanced Distribution Transformation","created":"2025-06-19","cited_by_count":6},{"id":"2503.19278","title":"Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines","created":"2025-03-25","cited_by_count":3},{"id":"2512.09235","title":"Efficient Feature Compression for Machines with Global Statistics Preservation","created":"2025-12-10","cited_by_count":3},{"id":"2410.02527","title":"Learning from Offline Foundation Features with Tensor Augmentations","created":"2024-10-03","cited_by_count":2},{"id":"2506.12737","title":"Cross-architecture universal feature coding via distribution alignment","created":"2025-06-15","cited_by_count":2},{"id":"2512.10230","title":"Emerging Standards for Machine-to-Machine Video Coding","created":"2025-12-11","cited_by_count":2},{"id":"2602.13555","title":"Privacy-Concealing Cooperative Perception for BEV Scene Segmentation","created":"2026-02-14","cited_by_count":2},{"id":"2502.14190","title":"Stereo Image Coding for Machines with Joint Visual Feature Compression","created":"2025-02-20","cited_by_count":1},{"id":"2506.07375","title":"DINO-CoDT: Multi-class Collaborative Detection and Tracking with Vision Foundation Models","created":"2025-06-09","cited_by_count":1},{"id":"2512.08227","title":"New VVC profiles targeting Feature Coding for Machines","created":"2025-12-09","cited_by_count":1},{"id":"2512.09232","title":"Enabling Next-Generation Consumer Experience with Feature Coding for Machines","created":"2025-12-10","cited_by_count":1},{"id":"2512.10209","title":"Feature Coding for Scalable Machine Vision","created":"2025-12-11","cited_by_count":1}],"next_cursor":null}