{"total":78,"rows":[{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2307.02628","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","created":"2023-07-05","cited_by_count":89,"area":"inference"},{"id":"2312.11462","title":"Cascade Speculative Drafting for Even Faster LLM Inference","created":"2023-12-18","cited_by_count":83,"area":"inference"},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67,"area":null},{"id":"2311.09755","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","created":"2023-11-16","cited_by_count":58,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2404.00725","title":"The Larger the Better? Improved LLM Code-Generation via Budget Reallocation","created":"2024-03-31","cited_by_count":43,"area":null},{"id":"2308.10462","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","created":"2023-08-21","cited_by_count":28,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"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":"2312.00968","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","created":"2023-12-01","cited_by_count":26,"area":"mllm"},{"id":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","cited_by_count":21,"area":null},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2211.07886","title":"A Survey for Efficient Open Domain Question Answering","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2405.10808","title":"ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios","created":"2024-05-17","cited_by_count":18,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2407.16235","title":"Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection","created":"2024-07-23","cited_by_count":18,"area":null},{"id":"2310.14451","title":"Domain Terminology Integration into Machine Translation: Leveraging Large Language Models","created":"2023-10-22","cited_by_count":17,"area":null},{"id":"2305.02031","title":"A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training","created":"2023-05-03","cited_by_count":16,"area":"distill"},{"id":"2406.18038","title":"MT2ST: Adaptive Multi-Task to Single-Task Learning","created":"2024-06-26","cited_by_count":16,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15,"area":null},{"id":"2406.19251","title":"AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation","created":"2024-06-27","cited_by_count":13,"area":"rag"},{"id":"2410.17170","title":"Self-calibration for Language Model Quantization and Pruning","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2302.10360","title":"Optical Transformers","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2305.16259","title":"Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2306.02870","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","cited_by_count":7,"area":null},{"id":"2408.15901","title":"Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts","created":"2024-08-28","cited_by_count":7,"area":"moe"},{"id":"2405.17025","title":"SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2306.02307","title":"Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings","created":"2023-06-04","cited_by_count":5,"area":"inference"},{"id":"2306.16900","title":"Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research","created":"2023-06-29","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":"2408.03274","title":"Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments","created":"2024-08-06","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2510.22763","title":"Iterative Layer Pruning for Efficient Translation Inference","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2408.16586","title":"Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2509.14608","title":"Enterprise AI Must Enforce Participant-Aware Access Control","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2305.19264","title":"Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2310.03283","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2401.07456","title":"Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2503.10643","title":"Synthetic Categorical Restructuring large Or How AIs Gradually Extract Efficient Regularities from Their Experience of the World","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2303.17612","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","created":"2023-03-30","cited_by_count":1,"area":null},{"id":"2305.19045","title":"Back to Patterns: Efficient Japanese Morphological Analysis with Feature-Sequence Trie","created":"2023-05-30","cited_by_count":1,"area":null},{"id":"2311.13731","title":"A Survey of Blockchain, Artificial Intelligence, and Edge Computing for Web 3.0","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2412.15785","title":"Learning from Impairment: Leveraging Insights from Clinical Linguistics in Language Modelling Research","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2508.06753","title":"Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.04821","title":"AFD-SLU: Adaptive Feature Distillation for Spoken Language Understanding","created":"2025-09-05","cited_by_count":1,"area":"distill"},{"id":"2511.06441","title":"Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2210.04466","title":"Investigating the Failure Modes of the AUC metric and Exploring Alternatives for Evaluating Systems in Safety Critical Applications","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2304.02481","title":"Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2311.03566","title":"Measuring Adversarial Datasets","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2401.12295","title":"Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2404.04759","title":"What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2404.08821","title":"Constrained C-Test Generation via Mixed-Integer Programming","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2405.13071","title":"A Novel Method for News Article Event-Based Embedding","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2503.05737","title":"Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2503.12992","title":"Intra-neuronal attention within language models Relationships between activation and semantics","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.07831","title":"Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2509.05729","title":"QCSE: A Pretrained Quantum Context-Sensitive Word Embedding for Natural Language Processing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2511.06391","title":"HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2601.18909","title":"How Is Uncertainty Propagated in Knowledge Distillation?","created":"2026-01-26","cited_by_count":0,"area":"distill"},{"id":"2606.07632","title":"Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.21806","title":"More Computational Resources Do Not Ensure Higher Scholarly Impact: Evidence from Leading NLP Conference Papers","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.29408","title":"An Integrated Vision-and-Language Pretraining (VLP) and Visual Question Answering (VQA) model to Automate Nondestructive Evaluation Image Analysis","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}