{"total":109,"rows":[{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763,"area":null},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316,"area":null},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"area":null},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124,"area":null},{"id":"2310.15819","title":"Generative Language Models Exhibit Social Identity Biases","created":"2023-10-24","cited_by_count":111,"area":null},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109,"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":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2406.07545","title":"Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena","created":"2024-06-11","cited_by_count":76,"area":null},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2404.14619","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","created":"2024-04-22","cited_by_count":75,"area":null},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73,"area":null},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72,"area":null},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2402.02385","title":"A Survey on Robotics with Foundation Models: toward Embodied AI","created":"2024-02-04","cited_by_count":56,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44,"area":"distill"},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","cited_by_count":37,"area":null},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36,"area":null},{"id":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35,"area":null},{"id":"2502.15672","title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling","created":"2025-02-21","cited_by_count":35,"area":"wm"},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2312.04828","title":"HuRef: HUman-REadable Fingerprint for Large Language Models","created":"2023-12-08","cited_by_count":34,"area":null},{"id":"2402.16840","title":"MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2401.17671","title":"Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain","created":"2024-01-31","cited_by_count":32,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2408.13359","title":"Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler","created":"2024-08-23","cited_by_count":28,"area":null},{"id":"2309.13322","title":"From Text to Source: Results in Detecting Large Language Model-Generated Content","created":"2023-09-23","cited_by_count":26,"area":"safety"},{"id":"2505.17716","title":"Get Experience from Practice: LLM Agents with Record & Replay","created":"2025-05-23","cited_by_count":23,"area":"agents"},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"id":"2309.11568","title":"BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model","created":"2023-09-20","cited_by_count":19,"area":null},{"id":"2412.09560","title":"Foundational Large Language Models for Materials Research","created":"2024-12-12","cited_by_count":18,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2307.00526","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","created":"2023-07-02","cited_by_count":17,"area":null},{"id":"2310.17876","title":"TarGEN: Targeted Data Generation with Large Language Models","created":"2023-10-27","cited_by_count":17,"area":null},{"id":"2403.15529","title":"LimGen: Probing the LLMs for Generating Suggestive Limitations of Research Papers","created":"2024-03-22","cited_by_count":16,"area":null},{"id":"2408.08310","title":"ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws","created":"2024-08-15","cited_by_count":15,"area":null},{"id":"2505.14733","title":"The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute","created":"2025-05-20","cited_by_count":15,"area":"lr"},{"id":"2601.10684","title":"On the origin of neural scaling laws: from random graphs to natural language","created":"2026-01-15","cited_by_count":14,"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":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2305.13102","title":"Observations on LLMs for Telecom Domain: Capabilities and Limitations","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2401.14489","title":"The Case for Co-Designing Model Architectures with Hardware","created":"2024-01-25","cited_by_count":11,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2401.16818","title":"H2O-Danube-1.8B Technical Report","created":"2024-01-30","cited_by_count":9,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2308.11103","title":"Anonymity at Risk? Assessing Re-Identification Capabilities of Large Language Models","created":"2023-08-22","cited_by_count":7,"area":null},{"id":"2310.04607","title":"A Comprehensive Performance Study of Large Language Models on Novel AI Accelerators","created":"2023-10-06","cited_by_count":7,"area":null},{"id":"2404.06003","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","created":"2024-04-09","cited_by_count":7,"area":null},{"id":"2411.00999","title":"Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2604.04722","title":"Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs","created":"2026-04-06","cited_by_count":7,"area":"inference"},{"id":"2304.06875","title":"nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales","created":"2023-04-14","cited_by_count":6,"area":null},{"id":"2310.00385","title":"Dynamic Demonstrations Controller for In-Context Learning","created":"2023-09-30","cited_by_count":6,"area":null},{"id":"2505.15270","title":"Scaling Diffusion Transformers Efficiently via $\\mu$P","created":"2025-05-21","cited_by_count":6,"area":"diffusion"},{"id":"2410.16703","title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2403.07921","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2410.05224","title":"Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2506.13274","title":"AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2604.13275","title":"Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2609.18094","title":"Agora: Git as Shared Memory for Collective AutoResearch","created":"2026-09-16","cited_by_count":3,"area":"agents"},{"id":"2308.10354","title":"Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2401.11459","title":"AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technology","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2410.10672","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.04890","title":"Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2602.04556","title":"Rethinking Weight Tying: Pseudo-Inverse Tying for LM Stable Training and Updates","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2606.20299","title":"Statistical Properties of Training & Generalization","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2306.06662","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","created":"2023-06-11","cited_by_count":1,"area":null},{"id":"2404.14419","title":"Evaluation and Improvement of Fault Detection for Large Language Models","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2405.19284","title":"Optimizing Foundation Model Inference on a Many-tiny-core Open-source RISC-V Platform","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2407.06955","title":"ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2505.06085","title":"Assessing Tenstorrent's RISC-V MatMul Acceleration Capabilities","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2510.21048","title":"xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2604.03199","title":"Learning the Signature of Memorization in Autoregressive Language Models","created":"2026-04-03","cited_by_count":1,"area":"safety"},{"id":"2605.15290","title":"GQA-{\\mu}P: The maximal parameterization update for grouped query attention","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.24077","title":"Sentence-Level Contextual Entrainment in Large Language Models","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2608.08139","title":"TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2608.17286","title":"Abra: Scaling Diffusion Image Training","created":"2026-08-18","cited_by_count":1,"area":"diffusion"},{"id":"2609.08981","title":"Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2305.10445","title":"Memorization for Good: Encryption with Autoregressive Language Models","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2308.00624","title":"JIANG: Chinese Open Foundation Language Model","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2404.13751","title":"Embarrassingly Simple Unsupervised Aspect Based Sentiment Tuple Extraction","created":"2024-04-21","cited_by_count":0,"area":null},{"id":"2407.03622","title":"MSfusion: A Dynamic Model Splitting Approach for Resource-Constrained Machines to Collaboratively Train Larger Models","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2504.01540","title":"From Sm{\\o}r-re-br{\\o}d to Subwords: Training LLMs on Danish, One Morpheme at a Time","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2506.06926","title":"Basis Transformers for Multi-Task Tabular Regression","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null}],"next_cursor":"100"}