{"total":26,"rows":[{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165,"area":null},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35,"area":null},{"id":"2402.16840","title":"MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26,"area":null},{"id":"2404.05657","title":"MLP Can Be A Good Transformer Learner","created":"2024-04-08","cited_by_count":17,"area":null},{"id":"2506.14562","title":"AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs","created":"2025-06-17","cited_by_count":13,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2305.11685","title":"Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2511.22686","title":"Emergent Extreme-View Geometry in 3D Foundation Models","created":"2025-11-27","cited_by_count":6,"area":null},{"id":"2402.11819","title":"Head-wise Shareable Attention for Large Language Models","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2402.17710","title":"Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2506.18233","title":"Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2602.08722","title":"QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2409.14595","title":"EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2503.21838","title":"MSPLoRA: A Multi-Scale Pyramid Low-Rank Adaptation for Efficient Model Fine-Tuning","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2506.16787","title":"Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2510.25979","title":"AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2506.09163","title":"Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2312.11466","title":"Extracting Interpretable Local and Global Representations from Attention on Time Series","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2505.21535","title":"FAR: Function-preserving Attention Replacement for IMC-friendly Inference","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2605.18865","title":"From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.39259","title":"Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}