{"total":137,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208,"area":null},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"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":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2205.13760","title":"Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval","created":"2022-05-27","cited_by_count":79,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2504.05295","title":"Dion: Distributed Orthonormalized Updates","created":"2025-04-07","cited_by_count":68,"area":null},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2207.02852","title":"Machine Learning Model Sizes and the Parameter Gap","created":"2022-07-05","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2111.04130","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","created":"2021-11-07","cited_by_count":34,"area":null},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2410.02703","title":"Selective Attention Improves Transformer","created":"2024-10-03","cited_by_count":26,"area":null},{"id":"2407.10969","title":"Q-Sparse: All Large Language Models can be Fully Sparsely-Activated","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2604.21106","title":"How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models","created":"2026-04-22","cited_by_count":24,"area":null},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2305.08404","title":"Theoretical Analysis of Inductive Biases in Deep Convolutional Networks","created":"2023-05-15","cited_by_count":21,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","cited_by_count":20,"area":null},{"id":"2205.05071","title":"Towards Climate Awareness in NLP Research","created":"2022-05-10","cited_by_count":19,"area":null},{"id":"2311.08610","title":"Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2207.13955","title":"Neural Architecture Search on Efficient Transformers and Beyond","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17,"area":null},{"id":"2308.13490","title":"TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","created":"2023-08-25","cited_by_count":16,"area":null},{"id":"2411.04965","title":"BitNet a4.8: 4-bit Activations for 1-bit LLMs","created":"2024-11-07","cited_by_count":16,"area":null},{"id":"2203.02094","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","created":"2022-03-04","cited_by_count":14,"area":null},{"id":"2205.02629","title":"Efficient yet Competitive Speech Translation: FBK@IWSLT2022","created":"2022-05-05","cited_by_count":14,"area":null},{"id":"2207.03509","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14,"area":null},{"id":"2312.06798","title":"Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2406.03348","title":"Position: A Call to Action for a Human-Centered AutoML Paradigm","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2302.09178","title":"Improving Training Stability for Multitask Ranking Models in Recommender Systems","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2410.16682","title":"Methods of improving LLM training stability","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2211.01842","title":"Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2306.00288","title":"Training-free Neural Architecture Search for RNNs and Transformers","created":"2023-06-01","cited_by_count":9,"area":null},{"id":"2411.03884","title":"Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models","created":"2024-11-06","cited_by_count":9,"area":null},{"id":"2503.16672","title":"Accelerating Transformer Inference and Training with 2:4 Activation Sparsity","created":"2025-03-20","cited_by_count":9,"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":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2408.14915","title":"Can Transformers Do Enumerative Geometry?","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2507.02754","title":"Fast and Simplex: 2-Simplicial Attention in Triton","created":"2025-07-03","cited_by_count":8,"area":null},{"id":"2309.03004","title":"A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2211.05187","title":"Training a Vision Transformer from scratch in less than 24 hours with 1 GPU","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2410.01779","title":"Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2507.01299","title":"La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation","created":"2025-07-02","cited_by_count":6,"area":null},{"id":"2509.23500","title":"Beyond Outliers: A Study of Optimizers Under Quantization","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2601.08517","title":"Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models","created":"2026-01-13","cited_by_count":6,"area":null},{"id":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2208.14111","title":"Transformers with Learnable Activation Functions","created":"2022-08-30","cited_by_count":5,"area":null},{"id":"2405.20838","title":"einspace: Searching for Neural Architectures from Fundamental Operations","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2411.13010","title":"Deriving Activation Functions Using Integration","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2205.03960","title":"Neural Architecture Search using Property Guided Synthesis","created":"2022-05-08","cited_by_count":4,"area":null},{"id":"2207.00081","title":"Sustainable Computing -- Without the Hot Air","created":"2022-06-30","cited_by_count":4,"area":null},{"id":"2210.05018","title":"LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds","created":"2022-10-10","cited_by_count":4,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2602.16375","title":"Variable-Length Semantic IDs for Recommender Systems","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2605.26355","title":"Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2605.17109","title":"DynMuon: A Dynamic Spectral Shaping View of Muon","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2210.14016","title":"Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2305.00723","title":"Predictions Based on Pixel Data: Insights from PDEs and Finite Differences","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2305.19082","title":"Embedding Inequalities for Barron-type Spaces","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2306.05176","title":"RRWKV: Capturing Long-range Dependencies in RWKV","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2503.07605","title":"SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.15366","title":"Sequence Modeling with Spectral Mean Flows","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2603.13381","title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","cited_by_count":2,"area":null}],"next_cursor":"100"}