{"total":64,"rows":[{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634,"area":"wm"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2406.10594","title":"BlockPruner: Fine-grained Pruning for Large Language Models","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"area":null},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2502.15618","title":"Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing","created":"2025-02-21","cited_by_count":14,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2411.16139","title":"Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2411.03513","title":"Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2504.04215","title":"Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability","created":"2025-04-05","cited_by_count":7,"area":"mechinterp"},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2512.02185","title":"Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2505.11788","title":"Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2510.12077","title":"Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2409.18996","title":"From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models","created":"2024-09-19","cited_by_count":4,"area":"lr"},{"id":"2411.12758","title":"An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2411.17847","title":"SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2503.17553","title":"Autonomous Radiotherapy Treatment Planning Using DOLA: A Privacy-Preserving, LLM-Based Optimization Agent","created":"2025-03-21","cited_by_count":4,"area":"agents"},{"id":"2504.07878","title":"Token Level Routing Inference System for Edge Devices","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2506.05413","title":"SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2510.02657","title":"Less LLM, More Documents: Searching for Improved RAG","created":"2025-10-03","cited_by_count":4,"area":"rag"},{"id":"2511.22334","title":"Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2409.11233","title":"Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2502.15443","title":"When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2504.10036","title":"DataPuzzle: Breaking Free from the Hallucinated Promise of LLMs in Data Analysis","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2503.01704","title":"DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2506.01967","title":"Turning LLM Activations Quantization-Friendly","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2509.06518","title":"Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.24257","title":"VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2408.08250","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2502.17728","title":"LLM Inference Acceleration via Efficient Operation Fusion","created":"2025-02-24","cited_by_count":1,"area":"inference"},{"id":"2505.21077","title":"Efficient Large Language Model Inference with Neural Block Linearization","created":"2025-05-27","cited_by_count":1,"area":"inference"},{"id":"2602.09509","title":"Beyond Student: An Asymmetric Network for Neural Network Inheritance","created":"2026-02-10","cited_by_count":1,"area":"distill"},{"id":"2606.09514","title":"BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference","created":"2026-06-08","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":"2405.15346","title":"BiSup: Bidirectional Quantization Error Suppression for Large Language Models","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2407.20557","title":"CELLM: An Efficient Communication in Large Language Models Training for Federated Learning","created":"2024-07-30","cited_by_count":0,"area":null},{"id":"2411.09580","title":"Software Performance Engineering for Foundation Model-Powered Software","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2411.16991","title":"Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models","created":"2024-11-25","cited_by_count":0,"area":"distill"},{"id":"2412.11494","title":"FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2412.15441","title":"Insights into resource utilization of code small language models serving with runtime engines and execution providers","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2412.16378","title":"REFA: Reference Free Alignment for multi-preference optimization","created":"2024-12-20","cited_by_count":0,"area":"alignment"},{"id":"2504.09803","title":"CUT: Pruning Pre-Trained Multi-Task Models into Compact Models for Edge Devices","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2506.05641","title":"Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2506.07695","title":"Towards a Small Language Model Lifecycle Framework","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.14440","title":"Model compression using knowledge distillation with integrated gradients","created":"2025-06-17","cited_by_count":0,"area":"distill"},{"id":"2511.12031","title":"Striking the Right Balance between Compute and Copy: Improving LLM Inferencing Under Speculative Decoding","created":"2025-11-15","cited_by_count":0,"area":"inference"},{"id":"2601.20408","title":"Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.00577","title":"SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution","created":"2026-01-31","cited_by_count":0,"area":"safety"},{"id":"2603.08173","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2608.03036","title":"LLM Serving in the Wild: An Empirical Study of Frameworks, Methods, and System Designs","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2609.22262","title":"Large language models in medical time series analysis","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}