{"total":81,"rows":[{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"area":null},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"area":null},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2109.15142","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","created":"2021-09-30","cited_by_count":31,"area":null},{"id":"2209.09570","title":"Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design","created":"2022-09-20","cited_by_count":31,"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":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"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":"2203.11239","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","created":"2022-03-21","cited_by_count":23,"area":null},{"id":"2305.08381","title":"Parameter-efficient Tuning of Large-scale Multimodal Foundation Model","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2409.07953","title":"What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?","created":"2024-09-12","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21,"area":null},{"id":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15,"area":null},{"id":"2106.02435","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","created":"2021-06-04","cited_by_count":14,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2408.01008","title":"Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs","created":"2024-08-02","cited_by_count":14,"area":null},{"id":"2210.05153","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2402.12138","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2202.12319","title":"Privacy-preserving machine learning with tensor networks","created":"2022-02-24","cited_by_count":9,"area":null},{"id":"2211.16749","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","created":"2022-11-30","cited_by_count":9,"area":null},{"id":"2401.02592","title":"Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2106.14742","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","created":"2021-06-28","cited_by_count":7,"area":null},{"id":"2206.11128","title":"tntorch: Tensor Network Learning with PyTorch","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2109.09075","title":"Adversarial Training with Contrastive Learning in NLP","created":"2021-09-19","cited_by_count":6,"area":null},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2308.16475","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","created":"2023-08-31","cited_by_count":5,"area":null},{"id":"2108.10764","title":"Regularizing Transformers With Deep Probabilistic Layers","created":"2021-08-23","cited_by_count":4,"area":null},{"id":"2410.02147","title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2410.03040","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.16032","title":"A Scalable Factorization Approach for High-Order Structured Tensor Recovery","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2205.12961","title":"Position: Tensor Networks are a Valuable Asset for Green AI","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2403.19500","title":"Tensor Network-Constrained Kernel Machines as Gaussian Processes","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2409.03295","title":"N-gram Prediction and Word Difference Representations for Language Modeling","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2501.06300","title":"Tensorization of neural networks for improved privacy and interpretability","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2501.06663","title":"Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2501.08727","title":"Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2601.17958","title":"TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors","created":"2026-01-25","cited_by_count":3,"area":null},{"id":"2207.14386","title":"Efficient NLP Model Finetuning via Multistage Data Filtering","created":"2022-07-28","cited_by_count":2,"area":null},{"id":"2306.01076","title":"Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2104.14741","title":"Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads","created":"2021-04-30","cited_by_count":1,"area":null},{"id":"2203.12814","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2207.04327","title":"Error Analysis of Tensor-Train Cross Approximation","created":"2022-07-09","cited_by_count":1,"area":null},{"id":"2207.05906","title":"Diverse Dance Synthesis via Keyframes with Transformer Controllers","created":"2022-07-13","cited_by_count":1,"area":null},{"id":"2208.12959","title":"Tensor Decomposition based Personalized Federated Learning","created":"2022-08-27","cited_by_count":1,"area":null},{"id":"2301.08374","title":"Projective Integral Updates for High-Dimensional Variational Inference","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2303.01166","title":"BPT: Binary Point Cloud Transformer for Place Recognition","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2306.15451","title":"Advancing Adversarial Training by Injecting Booster Signal","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2403.09998","title":"FBPT: A Fully Binary Point Transformer","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2410.20926","title":"Long Sequence Modeling with Attention Tensorization: From Sequence to Tensor Learning","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2412.02919","title":"Higher-Order Transformers With Kronecker-Structured Attention","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2608.30505","title":"Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2105.00812","title":"Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency","created":"2021-04-08","cited_by_count":0,"area":null},{"id":"2110.13032","title":"Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2309.02428","title":"Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2404.13808","title":"General Item Representation Learning for Cold-start Content Recommendations","created":"2024-04-22","cited_by_count":0,"area":null},{"id":"2405.10946","title":"Application of Tensorized Neural Networks for Cloud Classification","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2406.15370","title":"Traitement quantique des langues : {\\'e}tat de l'art","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2411.16914","title":"Curvature in the Looking-Glass: Optimal Methods to Exploit Curvature of Expectation in the Loss Landscape","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2412.12204","title":"SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2510.14161","title":"Data Understanding Survey: Pursuing Improved Dataset Characterization Via Tensor-based Methods","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.23917","title":"Tensor Computing Interface: An Application-Oriented, Lightweight Interface for Portable High-Performance Tensor Network Applications","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2604.14287","title":"Quantum-inspired tensor networks in machine learning models","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.25344","title":"A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.10677","title":"From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers","created":"2026-07-12","cited_by_count":0,"area":null}],"next_cursor":null}