{"total":118,"rows":[{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78,"area":null},{"id":"2406.17706","title":"FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model","created":"2024-06-25","cited_by_count":74,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2403.07652","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","created":"2024-03-12","cited_by_count":72,"area":"moe"},{"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":"2407.00945","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","created":"2024-07-01","cited_by_count":53,"area":"moe"},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47,"area":null},{"id":"2308.08758","title":"Discrete Prompt Compression with Reinforcement Learning","created":"2023-08-17","cited_by_count":42,"area":"inference"},{"id":"2202.08036","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","created":"2022-02-16","cited_by_count":37,"area":null},{"id":"2308.00255","title":"LGViT: Dynamic Early Exiting for Accelerating Vision Transformer","created":"2023-08-01","cited_by_count":31,"area":"inference"},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","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":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2301.08986","title":"Adapting a Language Model While Preserving its General Knowledge","created":"2023-01-21","cited_by_count":23,"area":null},{"id":"2312.15398","title":"Fairness-Aware Structured Pruning in Transformers","created":"2023-12-24","cited_by_count":22,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2210.12696","title":"On the Transformation of Latent Space in Fine-Tuned NLP Models","created":"2022-10-23","cited_by_count":19,"area":null},{"id":"2310.02998","title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","created":"2023-10-04","cited_by_count":19,"area":"mllm"},{"id":"2403.12983","title":"OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization","created":"2024-03-02","cited_by_count":18,"area":null},{"id":"2405.17890","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","created":"2024-05-28","cited_by_count":18,"area":"distill"},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2404.11536","title":"FedPFT: Federated Proxy Fine-Tuning of Foundation Models","created":"2024-04-17","cited_by_count":16,"area":null},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16,"area":null},{"id":"2303.06740","title":"Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study","created":"2023-03-12","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2403.08058","title":"CHAI: Clustered Head Attention for Efficient LLM Inference","created":"2024-03-12","cited_by_count":13,"area":"inference"},{"id":"2402.17304","title":"Probing Multimodal Large Language Models for Global and Local Semantic Representations","created":"2024-02-27","cited_by_count":12,"area":"mllm"},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2501.15674","title":"TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs","created":"2025-01-26","cited_by_count":12,"area":"lr"},{"id":"2510.12773","title":"Dr.LLM: Dynamic Layer Routing in LLMs","created":"2025-10-14","cited_by_count":12,"area":null},{"id":"2308.03449","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","created":"2023-08-07","cited_by_count":11,"area":null},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2401.12819","title":"Dynamic Layer Tying for Parameter-Efficient Transformers","created":"2024-01-23","cited_by_count":10,"area":"deeprl"},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2406.17296","title":"BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2410.01028","title":"Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity","created":"2024-10-01","cited_by_count":8,"area":"inference"},{"id":"2410.11772","title":"Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2310.09436","title":"Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2403.14919","title":"Hierarchical Skip Decoding for Efficient Autoregressive Text Generation","created":"2024-03-22","cited_by_count":7,"area":"inference"},{"id":"2406.06567","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","created":"2024-06-03","cited_by_count":7,"area":null},{"id":"2404.09326","title":"Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers","created":"2024-04-14","cited_by_count":6,"area":"distill"},{"id":"2405.20314","title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs","created":"2024-05-30","cited_by_count":6,"area":"inference"},{"id":"2410.14578","title":"Large Language Models Are Overparameterized Text Encoders","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2412.09812","title":"ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression","created":"2024-12-13","cited_by_count":6,"area":null},{"id":"2207.04993","title":"Embedding Recycling for Language Models","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2305.04940","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","created":"2023-05-08","cited_by_count":5,"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":"2310.04573","title":"Can pruning make Large Language Models more efficient?","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2405.02267","title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search","created":"2024-05-03","cited_by_count":5,"area":null},{"id":"2505.20237","title":"Efficient Speech Translation through Model Compression and Knowledge Distillation","created":"2025-05-26","cited_by_count":5,"area":"distill"},{"id":"2406.11187","title":"Save It All: Enabling Full Parameter Tuning for Federated Large Language Models via Cycle Block Gradient Descent","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2505.24451","title":"LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs","created":"2025-05-30","cited_by_count":4,"area":"mechinterp"},{"id":"2510.22763","title":"Iterative Layer Pruning for Efficient Translation Inference","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2608.10837","title":"TACTICL: Task-Aware Compression of Tabular ICL Models","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2201.12507","title":"AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models","created":"2022-01-29","cited_by_count":3,"area":"distill"},{"id":"2204.02601","title":"Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2301.06758","title":"Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers","created":"2023-01-17","cited_by_count":3,"area":null},{"id":"2305.08285","title":"Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2305.14706","title":"PruMUX: Augmenting Data Multiplexing with Model Compression","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2410.04941","title":"TOAST: Transformer Optimization using Adaptive and Simple Transformations","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2411.06506","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2503.01820","title":"RSQ: Learning from Important Tokens Leads to Better Quantized LLMs","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2506.00495","title":"FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.09093","title":"Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2510.00268","title":"Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2601.18302","title":"Suppressing Final Layer Hidden State Jumps in Transformer Pretraining","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"id":"2310.17491","title":"FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2311.12823","title":"EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2402.11700","title":"Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers","created":"2024-02-18","cited_by_count":2,"area":null},{"id":"2406.00061","title":"STAT: Shrinking Transformers After Training","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2407.15516","title":"Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2408.11858","title":"Convexity-based Pruning of Speech Representation Models","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2409.16302","title":"How Redundant Is the Transformer Stack in Speech Representation Models?","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2412.11242","title":"TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs","created":"2024-12-15","cited_by_count":2,"area":"inference"},{"id":"2507.05387","title":"The Generalization Ridge: Information Flow in Natural Language Generation","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2507.07954","title":"Input Conditioned Layer Dropping in Speech Foundation Models","created":"2025-07-10","cited_by_count":2,"area":null},{"id":"2509.26524","title":"TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2603.09865","title":"GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2201.03327","title":"Latency Adjustable Transformer Encoder for Language Understanding","created":"2022-01-10","cited_by_count":1,"area":null},{"id":"2306.05785","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2306.07061","title":"Deep Model Compression Also Helps Models Capture Ambiguity","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2403.04510","title":"Where does In-context Translation Happen in Large Language Models","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2409.14168","title":"Towards Building Efficient Sentence BERT Models using Layer Pruning","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2501.06126","title":"Merging Feed-Forward Sublayers for Compressed Transformers","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2505.14513","title":"Latent Flow Transformer","created":"2025-05-20","cited_by_count":1,"area":"diffusion"},{"id":"2507.20749","title":"Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study","created":"2025-07-28","cited_by_count":1,"area":"mllm"},{"id":"2512.19125","title":"SAP: Syntactic Attention Pruning for Transformer-based Language Models","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2606.02750","title":"On the Persistent Effects of Lexicality in Large Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.18246","title":"Variable-Width Transformers","created":"2026-06-16","cited_by_count":1,"area":null}],"next_cursor":"100"}