{"total":75,"rows":[{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2203.13224","title":"Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion","created":"2022-03-24","cited_by_count":102,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"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":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2106.10715","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","created":"2021-06-20","cited_by_count":52,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2211.04508","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","created":"2022-11-08","cited_by_count":35,"area":null},{"id":"2306.05406","title":"Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories","created":"2023-06-08","cited_by_count":34,"area":null},{"id":"2405.16156","title":"Mixture of In-Context Prompters for Tabular PFNs","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2110.08246","title":"Tricks for Training Sparse Translation Models","created":"2021-10-15","cited_by_count":17,"area":null},{"id":"2309.14763","title":"ConPET: Continual Parameter-Efficient Tuning for Large Language Models","created":"2023-09-26","cited_by_count":17,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2106.04279","title":"Staircase Attention for Recurrent Processing of Sequences","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"area":null},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2408.11869","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","created":"2024-08-19","cited_by_count":8,"area":null},{"id":"2205.12410","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2406.05360","title":"Flexible and Adaptable Summarization via Expertise Separation","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2403.07322","title":"A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2410.03529","title":"No Need to Talk: Asynchronous Mixture of Language Models","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2502.17771","title":"Sample Selection via Contrastive Fragmentation for Noisy Label Regression","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2507.23083","title":"Context-aware Rotary Position Embedding","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2411.01137","title":"Data movement limits to frontier model training","created":"2024-11-02","cited_by_count":3,"area":null},{"id":"2605.20032","title":"CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection","created":"2026-05-19","cited_by_count":3,"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":"2503.08067","title":"Context-aware Biases for Length Extrapolation","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2507.21567","title":"RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2301.05865","title":"Gated Self-supervised Learning For Improving Supervised Learning","created":"2023-01-14","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2604.21724","title":"Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.07500","title":"Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.17816","title":"Conservation Laws for Modern Neural Architectures","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2608.10416","title":"Riemann GeoResolver: A Non-Euclidean Attention Framework from Euclidean Resolver to Hyperbolic-Spherical Geometry","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.12923","title":"Dissecting GPU Utilization for LLM Inference on Nvidia Hopper","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2207.09588","title":"New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2302.00003","title":"The Power of External Memory in Increasing Predictive Model Capacity","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2310.10480","title":"G-SPEED: General SParse Efficient Editing MoDel","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2506.09954","title":"Vision Generalist Model: A Survey","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2510.27182","title":"SERFLOW: A Cross-Service Cost Optimization Framework for SLO-Aware Dynamic ML Inference","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.17616","title":"Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2603.24436","title":"Enes Causal Discovery","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2607.26192","title":"Dynamic Parameterization Is Not Dynamic Inference","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2610.02907","title":"Do ResNets Route? Sparse Interaction Experts in Residual Networks","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}