{"total":139,"rows":[{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120,"area":null},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"area":null},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44,"area":null},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32,"area":null},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30,"area":null},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2405.18378","title":"A Canonicalization Perspective on Invariant and Equivariant Learning","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2410.10254","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","created":"2024-10-14","cited_by_count":27,"area":null},{"id":"2406.06367","title":"MVGamba: Unify 3D Content Generation as State Space Sequence Modeling","created":"2024-06-10","cited_by_count":23,"area":"diffusion"},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2402.13934","title":"Do Efficient Transformers Really Save Computation?","created":"2024-02-21","cited_by_count":20,"area":null},{"id":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2404.03900","title":"Nonparametric Modern Hopfield Models","created":"2024-04-05","cited_by_count":16,"area":null},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16,"area":null},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2403.05822","title":"TrafficGPT: Breaking the Token Barrier for Efficient Long Traffic Analysis and Generation","created":"2024-03-09","cited_by_count":15,"area":null},{"id":"2408.04713","title":"DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"id":"2509.05486","title":"The Token Tax: Systematic Bias in Multilingual Tokenization","created":"2025-09-05","cited_by_count":14,"area":null},{"id":"2512.22748","title":"TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts","created":"2025-12-28","cited_by_count":14,"area":"mllm"},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2408.04093","title":"Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2403.05160","title":"MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models","created":"2024-03-08","cited_by_count":12,"area":"ssm"},{"id":"2502.00500","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","created":"2025-02-01","cited_by_count":11,"area":"diffusion"},{"id":"2605.09649","title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","created":"2026-05-10","cited_by_count":11,"area":"inference"},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10,"area":"ssm"},{"id":"2408.11451","title":"SIGMA: Selective Gated Mamba for Sequential Recommendation","created":"2024-08-21","cited_by_count":10,"area":"ssm"},{"id":"2410.04271","title":"Fundamental Limitations on Subquadratic Alternatives to Transformers","created":"2024-10-05","cited_by_count":9,"area":"ssm"},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2509.00320","title":"TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models","created":"2025-08-30","cited_by_count":9,"area":"mllm"},{"id":"2407.10998","title":"Discrete Diffusion Language Model for Efficient Text Summarization","created":"2024-06-25","cited_by_count":8,"area":"diffusion"},{"id":"2403.02920","title":"TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2406.02638","title":"EchoMamba4Rec: Harmonizing Bidirectional State Space Models with Spectral Filtering for Advanced Sequential Recommendation","created":"2024-06-04","cited_by_count":7,"area":"ssm"},{"id":"2409.12401","title":"MambaRecon: MRI Reconstruction with Structured State Space Models","created":"2024-09-19","cited_by_count":7,"area":"ssm"},{"id":"2509.09955","title":"Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge","created":"2025-09-12","cited_by_count":7,"area":"inference"},{"id":"2511.17209","title":"Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers","created":"2025-11-21","cited_by_count":7,"area":null},{"id":"2601.22136","title":"StepShield: When, Not Whether to Intervene on Rogue Agents","created":"2026-01-29","cited_by_count":7,"area":"safety"},{"id":"2402.15758","title":"Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens","created":"2024-02-24","cited_by_count":6,"area":"inference"},{"id":"2411.10057","title":"KuaiFormer: Transformer-Based Retrieval at Kuaishou","created":"2024-11-15","cited_by_count":6,"area":null},{"id":"2503.09956","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2512.05470","title":"Everything is Context: Agentic File System Abstraction for Context Engineering","created":"2025-12-05","cited_by_count":6,"area":"agents"},{"id":"2602.10056","title":"WildCat: Near-Linear Attention in Theory and Practice","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2210.06425","title":"MiniALBERT: Model Distillation via Parameter-Efficient Recursive Transformers","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2311.17956","title":"QuadraNet: Improving High-Order Neural Interaction Efficiency with Hardware-Aware Quadratic Neural Networks","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2502.00462","title":"MambaGlue: Fast and Robust Local Feature Matching With Mamba","created":"2025-02-01","cited_by_count":5,"area":"ssm"},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2505.14840","title":"Subquadratic Algorithms and Hardness for Attention with Any Temperature","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2407.19205","title":"Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions","created":"2024-07-27","cited_by_count":4,"area":"diffusion"},{"id":"2502.17481","title":"Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.06231","title":"WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models","created":"2025-03-08","cited_by_count":4,"area":"diffusion"},{"id":"2507.23539","title":"Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions","created":"2025-07-31","cited_by_count":4,"area":null},{"id":"2508.06993","title":"OctreeNCA: Single-Pass 184 MP Segmentation on Consumer Hardware","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2509.17791","title":"Elucidating the Design Space of FP4 training","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2510.13905","title":"Schema for In-Context Learning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2310.02544","title":"SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2311.01960","title":"Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2403.11026","title":"EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration","created":"2024-03-16","cited_by_count":3,"area":null},{"id":"2408.01018","title":"GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2409.01622","title":"T1-contrast Enhanced MRI Generation from Multi-parametric MRI for Glioma Patients with Latent Tumor Conditioning","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2410.24023","title":"RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2509.09001","title":"Fast attention mechanisms: a tale of parallelism","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2510.15966","title":"PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency","created":"2025-10-12","cited_by_count":3,"area":null},{"id":"2602.11175","title":"Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2402.09109","title":"Stochastic Spiking Attention: Accelerating Attention with Stochastic Computing in Spiking Networks","created":"2024-02-14","cited_by_count":2,"area":null},{"id":"2403.16272","title":"L-MAE: Longitudinal masked auto-encoder with time and severity-aware encoding for diabetic retinopathy progression prediction","created":"2024-03-24","cited_by_count":2,"area":null},{"id":"2408.09650","title":"From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2411.05593","title":"Evaluating and Adapting Large Language Models to Represent Folktales in Low-Resource Languages","created":"2024-11-08","cited_by_count":2,"area":null},{"id":"2502.08363","title":"Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2503.09850","title":"TabNSA: Native Sparse Attention for Efficient Tabular Data Learning","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.11083","title":"QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2507.07505","title":"Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models","created":"2025-07-10","cited_by_count":2,"area":"agents"},{"id":"2509.09168","title":"Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communication","created":"2025-09-11","cited_by_count":2,"area":"inference"},{"id":"2510.05901","title":"Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.14919","title":"Predicting Task Performance with Context-aware Scaling Laws","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2309.05795","title":"On the Fine-Grained Hardness of Inverting Generative Models","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2401.14845","title":"Adaptive Point Transformer","created":"2024-01-26","cited_by_count":1,"area":null},{"id":"2402.11729","title":"Prospector Heads: Generalized Feature Attribution for Large Models & Data","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2408.05952","title":"Optimizing Vision Transformers with Data-Free Knowledge Transfer","created":"2024-08-12","cited_by_count":1,"area":"distill"},{"id":"2410.09298","title":"DeepOSets: Non-Autoregressive In-Context Learning with Permutation-Invariance Inductive Bias","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2411.04013","title":"$k$NN Attention Demystified: A Theoretical Exploration for Scalable Transformers","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2504.00564","title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2507.04259","title":"An Explainable Transformer Model for Alzheimer's Disease Detection Using Retinal Imaging","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2511.15434","title":"Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2512.23329","title":"Deep learning for pedestrians: backpropagation in Transformers","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2602.02707","title":"Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.16704","title":"Reinforced Fast Weights with Next-Sequence Prediction","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.13306","title":"Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.03950","title":"Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2604.12047","title":"Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG","created":"2026-04-13","cited_by_count":1,"area":"rag"},{"id":"2605.11744","title":"Training-Inference Consistent Segmented Execution for Long-Context LLMs","created":"2026-05-12","cited_by_count":1,"area":null}],"next_cursor":"100"}