{"total":265,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864,"area":"diffusion"},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613,"area":null},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216,"area":null},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2311.16863","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","created":"2023-11-28","cited_by_count":191,"area":null},{"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":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93,"area":null},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92,"area":null},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57,"area":null},{"id":"2307.05532","title":"Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators","created":"2023-07-08","cited_by_count":56,"area":"alignment"},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55,"area":null},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53,"area":null},{"id":"2501.17047","title":"How Linguistics Learned to Stop Worrying and Love the Language Models","created":"2025-01-28","cited_by_count":51,"area":null},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50,"area":null},{"id":"2304.03271","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","created":"2023-04-06","cited_by_count":44,"area":null},{"id":"2302.08476","title":"Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning","created":"2023-02-16","cited_by_count":42,"area":null},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41,"area":null},{"id":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2407.01178","title":"$\\text{Memory}^3$: Language Modeling with Explicit Memory","created":"2024-07-01","cited_by_count":40,"area":"rag"},{"id":"2404.12484","title":"Neural Methods for Amortized Inference","created":"2024-04-18","cited_by_count":39,"area":null},{"id":"2306.08323","title":"How to estimate carbon footprint when training deep learning models? A guide and review","created":"2023-06-14","cited_by_count":34,"area":null},{"id":"2505.06371","title":"The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization","created":"2025-05-09","cited_by_count":33,"area":null},{"id":"2508.15734","title":"Measuring the environmental impact of delivering AI at Google Scale","created":"2025-08-21","cited_by_count":32,"area":null},{"id":"2404.15319","title":"The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark","created":"2024-04-03","cited_by_count":29,"area":null},{"id":"2305.03123","title":"ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review","created":"2023-04-13","cited_by_count":28,"area":null},{"id":"2407.04014","title":"Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems","created":"2024-07-04","cited_by_count":28,"area":"inference"},{"id":"2304.00958","title":"DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains","created":"2023-04-03","cited_by_count":27,"area":null},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27,"area":null},{"id":"2503.05804","title":"Holistically Evaluating the Environmental Impact of Creating Language Models","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2303.10725","title":"SIESTA: Efficient Online Continual Learning with Sleep","created":"2023-03-19","cited_by_count":24,"area":null},{"id":"2303.18171","title":"How Efficient Are Today's Continual Learning Algorithms?","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2407.16893","title":"The Price of Prompting: Profiling Energy Use in Large Language Models Inference","created":"2024-07-04","cited_by_count":23,"area":null},{"id":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"area":"distill"},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2412.04782","title":"A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges","created":"2024-12-06","cited_by_count":18,"area":null},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2407.00010","title":"Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads","created":"2024-04-25","cited_by_count":17,"area":null},{"id":"2311.04929","title":"An Interdisciplinary Outlook on Large Language Models for Scientific Research","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2405.03594","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment","created":"2024-05-06","cited_by_count":15,"area":null},{"id":"2402.16268","title":"Foundation Model Transparency Reports","created":"2024-02-26","cited_by_count":14,"area":null},{"id":"2306.01904","title":"Overcoming the Stability Gap in Continual Learning","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2401.06178","title":"AI Art is Theft: Labour, Extraction, and Exploitation, Or, On the Dangers of Stochastic Pollocks","created":"2024-01-10","cited_by_count":13,"area":null},{"id":"2401.16640","title":"TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese","created":"2024-01-30","cited_by_count":13,"area":null},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2404.00836","title":"Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm","created":"2024-04-01","cited_by_count":13,"area":null},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13,"area":"lr"},{"id":"2410.17170","title":"Self-calibration for Language Model Quantization and Pruning","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2505.16508","title":"Edge-First Language Model Inference: Models, Metrics, and Tradeoffs","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2309.02065","title":"Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2501.01990","title":"Towards Sustainable Large Language Model Serving","created":"2024-12-31","cited_by_count":12,"area":null},{"id":"2506.22696","title":"Residual Matrix Transformers: Scaling the Size of the Residual Stream","created":"2025-06-28","cited_by_count":12,"area":null},{"id":"2508.06097","title":"Recurrent Deep Differentiable Logic Gate Networks","created":"2025-08-08","cited_by_count":12,"area":null},{"id":"2511.05597","title":"From Prompts to Power: Measuring the Energy Footprint of LLM Inference","created":"2025-11-05","cited_by_count":12,"area":null},{"id":"2311.10267","title":"Energy and Carbon Considerations of Fine-Tuning BERT","created":"2023-11-17","cited_by_count":11,"area":null},{"id":"2402.13432","title":"DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2602.23225","title":"Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2303.06219","title":"The Carbon Emissions of Writing and Illustrating Are Lower for AI than for Humans","created":"2023-03-08","cited_by_count":10,"area":null},{"id":"2307.05494","title":"Towards Environmentally Equitable AI via Geographical Load Balancing","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2409.11416","title":"The Unseen AI Disruptions for Power Grids: LLM-Induced Transients","created":"2024-09-09","cited_by_count":10,"area":null},{"id":"2502.01671","title":"Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends","created":"2025-02-01","cited_by_count":10,"area":null},{"id":"2505.04416","title":"OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models","created":"2025-05-07","cited_by_count":10,"area":"safety"},{"id":"2308.12908","title":"POLCA: Power Oversubscription in LLM Cloud Providers","created":"2023-08-24","cited_by_count":9,"area":null},{"id":"2311.02597","title":"FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM","created":"2023-11-05","cited_by_count":9,"area":"rag"},{"id":"2407.02772","title":"Gradient descent with generalized Newton's method","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2503.21023","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","created":"2025-03-26","cited_by_count":9,"area":null},{"id":"2305.12987","title":"GPT-SW3: An Autoregressive Language Model for the Nordic Languages","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2306.01497","title":"Data-Efficient French Language Modeling with CamemBERTa","created":"2023-06-02","cited_by_count":8,"area":null},{"id":"2401.11316","title":"PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation","created":"2024-01-20","cited_by_count":8,"area":null},{"id":"2406.05303","title":"Beyond Efficiency: Scaling AI Sustainably","created":"2024-06-08","cited_by_count":8,"area":null},{"id":"2410.05565","title":"Chain and Causal Attention for Efficient Entity Tracking","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2505.01731","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","created":"2025-05-03","cited_by_count":8,"area":null},{"id":"2506.01774","title":"Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2509.22092","title":"Ground-Truthing AI Energy Consumption: Validating CodeCarbon Against External Measurements","created":"2025-09-26","cited_by_count":8,"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":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","cited_by_count":7,"area":null},{"id":"2403.03344","title":"Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2405.02385","title":"Efficient Deep Learning with Decorrelated Backpropagation","created":"2024-05-03","cited_by_count":7,"area":null},{"id":"2407.10804","title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2311.03615","title":"CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers","created":"2023-11-06","cited_by_count":6,"area":null},{"id":"2403.13638","title":"Pretraining Language Models Using Translationese","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2406.17972","title":"LABOR-LLM: Language-Based Occupational Representations with Large Language Models","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2407.04173","title":"Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2503.09956","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2505.20761","title":"Practical estimation of the optimal classification error with soft labels and calibration","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2510.05307","title":"When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2312.14647","title":"Towards Message Brokers for Generative AI: Survey, Challenges, and Opportunities","created":"2023-12-22","cited_by_count":5,"area":null},{"id":"2409.18664","title":"How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models","created":"2024-09-27","cited_by_count":5,"area":null}],"next_cursor":"100"}