{"list":"other","total":132,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2006.10685","title":"Deep Learning Enabled Semantic Communication Systems","created":"2020-06-18","cited_by_count":292},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"2011.14844","title":"6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications","created":"2020-11-04","cited_by_count":112},{"id":"2102.12605","title":"Semantic Communication Systems for Speech Transmission","created":"2021-02-24","cited_by_count":97},{"id":"1911.11174","title":"DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback","created":"2019-11-25","cited_by_count":96},{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61},{"id":"2206.04011","title":"Robust Semantic Communications with Masked VQ-VAE Enabled Codebook","created":"2022-06-08","cited_by_count":56},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52},{"id":"2108.07357","title":"Task-Oriented Multi-User Semantic Communications for VQA Task","created":"2021-08-16","cited_by_count":51},{"id":"2204.07790","title":"Wireless Semantic Communications for Video Conferencing","created":"2022-04-16","cited_by_count":50},{"id":"2501.10064","title":"One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression","created":"2025-01-17","cited_by_count":48},{"id":"2104.02138","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","created":"2021-04-05","cited_by_count":42},{"id":"2411.08872","title":"Large Wireless Model (LWM): A Foundation Model for Wireless Channels","created":"2024-11-13","cited_by_count":40},{"id":"2510.12872","title":"KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems","created":"2025-10-14","cited_by_count":40},{"id":"2206.08100","title":"DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding","created":"2022-06-16","cited_by_count":38},{"id":"2401.00124","title":"Generative AI-driven Semantic Communication Networks: Architecture, Technologies and Applications","created":"2023-12-30","cited_by_count":36},{"id":"2307.03492","title":"Large AI Model-Based Semantic Communications","created":"2023-07-07","cited_by_count":35},{"id":"2502.12096","title":"Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications","created":"2025-02-17","cited_by_count":35},{"id":"2205.04603","title":"Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis","created":"2022-05-09","cited_by_count":33},{"id":"2505.11432","title":"MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production","created":"2025-05-16","cited_by_count":31},{"id":"2309.00470","title":"Deep Joint Source-Channel Coding for Adaptive Image Transmission over MIMO Channels","created":"2023-09-01","cited_by_count":28},{"id":"2502.01189","title":"Compressed Image Generation with Denoising Diffusion Codebook Models","created":"2025-02-03","cited_by_count":28},{"id":"2403.17256","title":"Latency-Aware Generative Semantic Communications with Pre-Trained Diffusion Models","created":"2024-03-25","cited_by_count":25},{"id":"2405.01221","title":"A Survey on Semantic Communication Networks: Architecture, Security, and Privacy","created":"2024-05-02","cited_by_count":22},{"id":"2308.15483","title":"Generative AI for Semantic Communication: Architecture, Challenges, and Outlook","created":"2023-08-03","cited_by_count":20},{"id":"2403.07338","title":"D$^2$-JSCC: Digital Deep Joint Source-channel Coding for Semantic Communications","created":"2024-03-12","cited_by_count":20},{"id":"2408.08707","title":"Beam Prediction based on Large Language Models","created":"2024-08-16","cited_by_count":20},{"id":"2407.18468","title":"Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints","created":"2024-07-26","cited_by_count":19},{"id":"2412.12687","title":"Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models","created":"2024-12-17","cited_by_count":19},{"id":"2506.08257","title":"Highly Compressed Tokenizer Can Generate Without Training","created":"2025-06-09","cited_by_count":18},{"id":"2207.01843","title":"Twelve Scientific Challenges for 6G: Rethinking the Foundations of Communications Theory","created":"2022-07-05","cited_by_count":15},{"id":"2302.07142","title":"Semantic Importance-Aware Communications Using Pre-trained Language Models","created":"2023-02-12","cited_by_count":15},{"id":"1906.09867","title":"Compressive Sensing Based Adaptive Active User Detection and Channel Estimation: Massive Access Meets Massive MIMO","created":"2019-06-24","cited_by_count":14},{"id":"2203.16005","title":"Deep Joint Source-Channel Coding for CSI Feedback: An End-to-End Approach","created":"2022-03-30","cited_by_count":14},{"id":"2505.17604","title":"Adaptive Semantic Token Communication for Transformer-based Edge Inference","created":"2025-05-23","cited_by_count":14},{"id":"2202.03705","title":"A Survey on Semantic Communications for Intelligent Wireless Networks","created":"2022-02-08","cited_by_count":13},{"id":"2406.06644","title":"Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises","created":"2024-06-09","cited_by_count":13},{"id":"2412.20772","title":"Large Language Model Enabled Multi-Task Physical Layer Network","created":"2024-12-30","cited_by_count":13},{"id":"2407.00020","title":"Visual Language Model based Cross-modal Semantic Communication Systems","created":"2024-05-06","cited_by_count":12},{"id":"2507.05938","title":"A Wireless Foundation Model for Multi-Task Prediction","created":"2025-07-08","cited_by_count":12},{"id":"2507.01728","title":"Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach","created":"2025-07-02","cited_by_count":11},{"id":"2112.10086","title":"Heterogeneous Transformer: A Scale Adaptable Neural Network Architecture for Device Activity Detection","created":"2021-12-19","cited_by_count":10},{"id":"2405.02330","title":"Adaptive Semantic Token Selection for AI-native Goal-oriented Communications","created":"2024-04-25","cited_by_count":10},{"id":"2502.13838","title":"Generative Video Semantic Communication via Multimodal Semantic Fusion with Large Model","created":"2025-02-19","cited_by_count":9},{"id":"2503.14882","title":"Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks","created":"2025-03-19","cited_by_count":9},{"id":"2301.00433","title":"Optimization of Image Transmission in a Cooperative Semantic Communication Networks","created":"2023-01-01","cited_by_count":8},{"id":"2409.09715","title":"Generative Semantic Communication via Textual Prompts: Latency Performance Tradeoffs","created":"2024-09-15","cited_by_count":8},{"id":"2411.15845","title":"Space-ground Fluid AI for 6G Edge Intelligence","created":"2024-11-24","cited_by_count":8},{"id":"2310.09506","title":"Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches","created":"2023-10-14","cited_by_count":7},{"id":"2404.06997","title":"Agent-driven Generative Semantic Communication with Cross-Modality and Prediction","created":"2024-04-10","cited_by_count":7},{"id":"2408.04535","title":"Synchronous Multi-modal Semantic Communication System with Packet-level Coding","created":"2024-08-08","cited_by_count":7},{"id":"2505.10946","title":"ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access","created":"2025-05-16","cited_by_count":7},{"id":"2507.06567","title":"SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference","created":"2025-07-09","cited_by_count":7},{"id":"2509.09955","title":"Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge","created":"2025-09-12","cited_by_count":7},{"id":"2511.15699","title":"Joint Semantic-Channel Coding and Modulation for Token Communications","created":"2025-11-19","cited_by_count":7},{"id":"2606.05711","title":"Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems","created":"2026-06-04","cited_by_count":7},{"id":"2411.18005","title":"Generative Semantic Communication for Joint Image Transmission and Segmentation","created":"2024-11-27","cited_by_count":6},{"id":"2309.12775","title":"Semantic Change Driven Generative Semantic Communication Framework","created":"2023-09-22","cited_by_count":5},{"id":"2311.13789","title":"Knowledge Distillation Based Semantic Communications For Multiple Users","created":"2023-11-23","cited_by_count":5},{"id":"2411.02334","title":"Communicate Less, Synthesize the Rest: Latency-aware Intent-based Generative Semantic Multicasting with Diffusion Models","created":"2024-11-04","cited_by_count":5},{"id":"2412.08642","title":"Generative Semantic Communication: Architectures, Technologies, and Applications","created":"2024-12-11","cited_by_count":5},{"id":"2506.19451","title":"Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search","created":"2025-06-24","cited_by_count":5},{"id":"2603.02470","title":"Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding","created":"2026-03-02","cited_by_count":5},{"id":"2401.09127","title":"AI Empowered Channel Semantic Acquisition for 6G Integrated Sensing and Communication Networks","created":"2024-01-17","cited_by_count":4},{"id":"2404.08490","title":"SemHARQ: Semantic-Aware Hybrid Automatic Repeat Request for Multi-Task Semantic Communications","created":"2024-04-12","cited_by_count":4},{"id":"2405.19889","title":"Deep Joint Semantic Coding and Beamforming for Near-Space Airship-Borne Massive MIMO Network","created":"2024-05-30","cited_by_count":4},{"id":"2407.05487","title":"Multi-level Reliability Interface for Semantic Communications over Wireless Networks","created":"2024-07-07","cited_by_count":4},{"id":"2502.10812","title":"ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling","created":"2025-02-15","cited_by_count":4},{"id":"2504.19591","title":"Semantic Packet Aggregation for Token Communication via Genetic Beam Search","created":"2025-04-28","cited_by_count":4},{"id":"2509.04576","title":"Communication-Efficient Collaborative LLM Inference via Distributed Speculative Decoding","created":"2025-09-04","cited_by_count":4}],"next_cursor":"100"}