{"total":46,"rows":[{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55,"area":null},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2402.07440","title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2312.08598","title":"MotherNet: Fast Training and Inference via Hyper-Network Transformers","created":"2023-12-14","cited_by_count":19,"area":null},{"id":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2410.03766","title":"FutureFill: Fast Generation from Convolutional Sequence Models","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2407.16847","title":"SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2505.18698","title":"MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2410.17477","title":"Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2408.00386","title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2410.12982","title":"Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2604.14724","title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2312.00412","title":"SCHEME: Scalable Channel Mixer for Vision Transformers","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2409.01482","title":"Masked Mixers for Language Generation and Retrieval","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2510.12111","title":"Chimera: State Space Models Beyond Sequences","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2404.00648","title":"SpiralMLP: A Lightweight Vision MLP Architecture","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2406.06290","title":"Geometric sparsification in recurrent neural networks","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2409.14986","title":"Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2412.11008","title":"Towards Context-aware Convolutional Network for Image Restoration","created":"2024-12-15","cited_by_count":1,"area":null},{"id":"2505.21468","title":"Causal Posterior Estimation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2510.20926","title":"FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fiction","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.18248","title":"Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2605.00292","title":"Caracal: Causal Architecture via Spectral Mixing","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2405.15013","title":"Fast Inference with Kronecker-Sparse Matrices","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2412.18437","title":"MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2503.08292","title":"Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2506.12475","title":"Efficient Star Distillation Attention Network for Lightweight Image Super-Resolution","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2510.11192","title":"Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2605.06628","title":"LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06683","title":"Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.08451","title":"RubiConv -- Efficient Boundary-Respecting Convolutions","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2608.29899","title":"REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2610.04720","title":"WNet: Discrete Wavelets Transform for Efficient Token Mixing","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}