{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"1412.0035","title":"Understanding Deep Image Representations by Inverting Them","created":"2014-11-26","cited_by_count":403},{"id":"2304.08247","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","created":"2023-04-14","cited_by_count":286},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"2406.19707","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","created":"2024-06-28","cited_by_count":245},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"1906.02059","title":"Neural Legal Judgment Prediction in English","created":"2019-06-05","cited_by_count":209},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"2405.06823","title":"PLeak: Prompt Leaking Attacks against Large Language Model Applications","created":"2024-05-10","cited_by_count":127},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122},{"id":"2406.06282","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","created":"2024-06-10","cited_by_count":103},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94},{"id":"2402.04401","title":"Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning","created":"2024-02-06","cited_by_count":90},{"id":"2307.06865","title":"Effective Prompt Extraction from Language Models","created":"2023-07-13","cited_by_count":85},{"id":"2311.13647","title":"Language Model Inversion","created":"2023-11-22","cited_by_count":68},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67},{"id":"2004.05703","title":"DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments","created":"2020-04-12","cited_by_count":58},{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58},{"id":"2503.00177","title":"Steering Large Language Model Activations in Sparse Spaces","created":"2025-02-28","cited_by_count":58},{"id":"1808.04761","title":"Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures","created":"2018-08-14","cited_by_count":57},{"id":"2503.02614","title":"Personalized Generation In Large Model Era: A Survey","created":"2025-03-04","cited_by_count":45},{"id":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41},{"id":"2010.10784","title":"Learning to Embed Categorical Features without Embedding Tables for Recommendation","created":"2020-10-21","cited_by_count":38},{"id":"2409.20002","title":"The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems","created":"2024-09-30","cited_by_count":29},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25},{"id":"2011.05905","title":"ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks","created":"2020-11-11","cited_by_count":21},{"id":"2310.07152","title":"No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML","created":"2023-10-11","cited_by_count":21},{"id":"2508.09442","title":"Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference","created":"2025-08-13","cited_by_count":21},{"id":"2507.16372","title":"Depth Gives a False Sense of Privacy: LLM Internal States Inversion","created":"2025-07-22","cited_by_count":17},{"id":"2310.04361","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","created":"2023-10-06","cited_by_count":16},{"id":"2411.18191","title":"InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks","created":"2024-11-27","cited_by_count":16},{"id":"2208.10134","title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","created":"2022-08-22","cited_by_count":15},{"id":"2408.13442","title":"A Law of Next-Token Prediction in Large Language Models","created":"2024-08-24","cited_by_count":15},{"id":"2503.09022","title":"Prompt Inversion Attack against Collaborative Inference of Large Language Models","created":"2025-03-12","cited_by_count":15},{"id":"2402.05526","title":"Buffer Overflow in Mixture of Experts","created":"2024-02-08","cited_by_count":13},{"id":"2508.15036","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","created":"2025-08-20","cited_by_count":13},{"id":"2410.22884","title":"Stealing User Prompts from Mixture of Experts","created":"2024-10-30","cited_by_count":12},{"id":"2412.01380","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","created":"2024-12-02","cited_by_count":11},{"id":"1511.04594","title":"Flush+Flush: A Fast and Stealthy Cache Attack","created":"2015-11-14","cited_by_count":10},{"id":"2411.03357","title":"PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption","created":"2024-11-04","cited_by_count":10},{"id":"2505.06738","title":"I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference","created":"2025-05-10","cited_by_count":7},{"id":"1912.01701","title":"An Off-Chip Attack on Hardware Enclaves via the Memory Bus","created":"2019-12-03","cited_by_count":6},{"id":"2505.23817","title":"System Prompt Extraction Attacks and Defenses in Large Language Models","created":"2025-05-27","cited_by_count":6},{"id":"2509.18886","title":"Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs","created":"2025-09-23","cited_by_count":5},{"id":"2511.13717","title":"TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone","created":"2025-11-17","cited_by_count":5},{"id":"2404.00190","title":"GuaranTEE: Towards Attestable and Private ML with CCA","created":"2024-03-29","cited_by_count":3},{"id":"2004.11071","title":"SEVurity: No Security Without Integrity -- Breaking Integrity-Free Memory Encryption with Minimal Assumptions","created":"2020-04-23","cited_by_count":2},{"id":"2503.19142","title":"Activation Functions Considered Harmful: Recovering Neural Network Weights through Controlled Channels","created":"2025-03-24","cited_by_count":2}],"next_cursor":null}