{"total":702,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465,"area":"ssm"},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627,"area":null},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897,"area":"wm"},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708,"area":null},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623,"area":"moe"},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618,"area":null},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424,"area":null},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"area":"moe"},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368,"area":null},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340,"area":"diffusion"},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2103.07719","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","created":"2021-03-13","cited_by_count":299,"area":null},{"id":"2205.13671","title":"Transformer for Partial Differential Equations' Operator Learning","created":"2022-05-26","cited_by_count":283,"area":null},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265,"area":null},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242,"area":null},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179,"area":"mechinterp"},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174,"area":"ssm"},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2501.15383","title":"Qwen2.5-1M Technical Report","created":"2025-01-26","cited_by_count":164,"area":null},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2306.15006","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","created":"2023-06-26","cited_by_count":143,"area":null},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"id":"2101.04775","title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis","created":"2021-01-12","cited_by_count":140,"area":null},{"id":"2303.14483","title":"Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey","created":"2023-03-25","cited_by_count":140,"area":null},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136,"area":"offlinerl"},{"id":"2208.12266","title":"Decoding speech perception from non-invasive brain recordings","created":"2022-08-25","cited_by_count":130,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120,"area":null},{"id":"2310.19923","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","created":"2023-10-30","cited_by_count":104,"area":null},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103,"area":null},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2305.17161","title":"Flow Matching for Scalable Simulation-Based Inference","created":"2023-05-26","cited_by_count":101,"area":"diffusion"},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93,"area":null},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2111.03600","title":"Hybrid Spectrogram and Waveform Source Separation","created":"2021-11-05","cited_by_count":91,"area":null},{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2106.00085","title":"Language Model Evaluation Beyond Perplexity","created":"2021-05-31","cited_by_count":78,"area":null},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"area":null},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2407.10172","title":"Restoring Images in Adverse Weather Conditions via Histogram Transformer","created":"2024-07-14","cited_by_count":73,"area":null},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72,"area":null},{"id":"2209.15174","title":"Music Source Separation with Band-split RNN","created":"2022-09-30","cited_by_count":70,"area":null},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68,"area":null},{"id":"2309.06979","title":"Auto-Regressive Next-Token Predictors are Universal Learners","created":"2023-09-13","cited_by_count":67,"area":"lr"},{"id":"2104.05522","title":"Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx","created":"2021-04-12","cited_by_count":64,"area":null},{"id":"2110.07732","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2311.07125","title":"Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification","created":"2023-11-13","cited_by_count":61,"area":null},{"id":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2204.13767","title":"Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version","created":"2022-04-28","cited_by_count":59,"area":null},{"id":"2306.10619","title":"Towards Stability of Autoregressive Neural Operators","created":"2023-06-18","cited_by_count":59,"area":null},{"id":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59,"area":"ssm"},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2406.15007","title":"RouteFinder: Towards Foundation Models for Vehicle Routing Problems","created":"2024-06-21","cited_by_count":55,"area":null},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"area":null},{"id":"2107.02960","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","created":"2021-07-07","cited_by_count":53,"area":null},{"id":"2402.10350","title":"Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review","created":"2024-02-15","cited_by_count":53,"area":null},{"id":"2208.02813","title":"Towards Understanding Mixture of Experts in Deep Learning","created":"2022-08-04","cited_by_count":52,"area":"moe"},{"id":"2406.02486","title":"A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting","created":"2024-06-04","cited_by_count":52,"area":null},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2112.02962","title":"DANets: Deep Abstract Networks for Tabular Data Classification and Regression","created":"2021-12-06","cited_by_count":50,"area":null},{"id":"2112.11174","title":"AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version","created":"2021-12-21","cited_by_count":48,"area":null},{"id":"2205.01138","title":"Transformers in Time-series Analysis: A Tutorial","created":"2022-04-28","cited_by_count":46,"area":null},{"id":"2405.17394","title":"The Expressive Capacity of State Space Models: A Formal Language Perspective","created":"2024-05-27","cited_by_count":46,"area":null},{"id":"2309.12252","title":"Parallelizing non-linear sequential models over the sequence length","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"2402.13516","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","created":"2024-02-21","cited_by_count":45,"area":"inference"},{"id":"2109.01163","title":"Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition","created":"2021-08-31","cited_by_count":42,"area":null},{"id":"2306.15789","title":"Structured State Space Models for Multiple Instance Learning in Digital Pathology","created":"2023-06-27","cited_by_count":41,"area":"ssm"},{"id":"2302.02173","title":"A Survey on Deep Learning based Time Series Analysis with Frequency Transformation","created":"2023-02-04","cited_by_count":40,"area":null},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40,"area":null},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2404.14999","title":"A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data","created":"2024-04-23","cited_by_count":39,"area":null},{"id":"2410.03943","title":"Oscillatory State-Space Models","created":"2024-10-04","cited_by_count":39,"area":null},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null}],"next_cursor":"100"}