{"total":118,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2411.02038","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","created":"2024-11-04","cited_by_count":80,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63,"area":null},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2501.16975","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","created":"2025-01-28","cited_by_count":44,"area":null},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2411.09009","title":"Cut Your Losses in Large-Vocabulary Language Models","created":"2024-11-13","cited_by_count":40,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2502.17599","title":"MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference","created":"2025-02-24","cited_by_count":31,"area":"mllm"},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2505.19227","title":"Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law","created":"2025-05-25","cited_by_count":24,"area":null},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2502.01637","title":"Scaling Embedding Layers in Language Models","created":"2025-02-03","cited_by_count":20,"area":null},{"id":"2502.14856","title":"FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling","created":"2025-02-20","cited_by_count":20,"area":"inference"},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2510.05197","title":"Efficient Prediction of Pass@k Scaling in Large Language Models","created":"2025-10-06","cited_by_count":16,"area":null},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15,"area":"inference"},{"id":"2601.21204","title":"Scaling Embeddings Outperforms Scaling Experts in Language Models","created":"2026-01-29","cited_by_count":15,"area":"moe"},{"id":"2502.01481","title":"Intrinsic Entropy of Context Length Scaling in LLMs","created":"2025-02-03","cited_by_count":14,"area":null},{"id":"2502.15343","title":"Tokenization is Sensitive to Language Variation","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2505.05713","title":"Understanding Stragglers in Large Model Training Using What-if Analysis","created":"2025-05-09","cited_by_count":12,"area":null},{"id":"2506.10766","title":"One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers","created":"2025-06-12","cited_by_count":12,"area":null},{"id":"2506.03101","title":"Beyond Text Compression: Evaluating Tokenizers Across Scales","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2412.15210","title":"Tokenisation is NP-Complete","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2503.12294","title":"The Lucie-7B LLM and the Lucie Training Dataset: Open resources for multilingual language generation","created":"2025-03-15","cited_by_count":10,"area":null},{"id":"2505.12716","title":"Shadow-FT: Tuning Instruct Model via Training on Paired Base Model","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2502.16880","title":"CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter","created":"2025-02-24","cited_by_count":9,"area":"inference"},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2409.09808","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","created":"2024-09-15","cited_by_count":8,"area":"ssm"},{"id":"2507.12720","title":"FLEXITOKENS: Flexible Tokenization for Evolving Language Models","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2510.00537","title":"Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2502.17262","title":"Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2408.09895","title":"Performance Law of Large Language Models","created":"2024-08-19","cited_by_count":6,"area":null},{"id":"2410.16257","title":"Elucidating the design space of language models for image generation","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2411.10057","title":"KuaiFormer: Transformer-Based Retrieval at Kuaishou","created":"2024-11-15","cited_by_count":6,"area":null},{"id":"2506.15025","title":"Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2507.23777","title":"XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding","created":"2025-07-31","cited_by_count":6,"area":"inference"},{"id":"2509.25522","title":"Understanding Generative Recommendation with Semantic IDs from a Model-scaling View","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2601.13260","title":"Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2602.13836","title":"Speculative Decoding with a Speculative Vocabulary","created":"2026-02-14","cited_by_count":6,"area":"inference"},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.18836","title":"From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2507.05557","title":"Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2510.03313","title":"Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2512.14954","title":"Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation","created":"2025-12-16","cited_by_count":5,"area":"distill"},{"id":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2410.18952","title":"Dynamic Vocabulary Pruning in Early-Exit LLMs","created":"2024-10-24","cited_by_count":4,"area":"inference"},{"id":"2411.04530","title":"Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts?","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2504.15431","title":"Trillion 7B Technical Report","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2510.13847","title":"DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models","created":"2025-10-11","cited_by_count":4,"area":"inference"},{"id":"2512.20757","title":"TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2602.11174","title":"The Script Tax: Measuring Tokenization-Driven Efficiency and Latency Disparities in Multilingual Language Models","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2605.01188","title":"Compute Optimal Tokenization","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2411.05281","title":"Fox-1: Open Small Language Model for Cloud and Edge","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2502.17910","title":"Scaling LLM Pre-training with Vocabulary Curriculum","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2504.15120","title":"Kuwain 1.5B: An Arabic SLM via Language Injection","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2508.11857","title":"SupraTok: Cross-Boundary Tokenization for Enhanced Language Model Performance","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2509.23437","title":"Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2510.05699","title":"Membership Inference Attacks on Tokenizers of Large Language Models","created":"2025-10-07","cited_by_count":3,"area":"safety"},{"id":"2511.11238","title":"Virtual Width Networks","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2512.13491","title":"From Zipf's Law to Neural Scaling through Heaps' Law and Hilberg's Hypothesis","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2601.21420","title":"ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation","created":"2026-01-29","cited_by_count":3,"area":"moe"},{"id":"2602.00800","title":"JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation","created":"2026-01-31","cited_by_count":3,"area":"moe"},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2604.22753","title":"Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2506.07833","title":"Improving Large Language Models with Concept-Aware Fine-Tuning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2603.14591","title":"FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2604.27263","title":"Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2410.12325","title":"$M^3$ Scaling Law: Optimizing Multi-Epoch, Multi-Lingual, and Multi-Stage Training for Low-Resource Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2411.03260","title":"ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow Removal","created":"2024-11-05","cited_by_count":1,"area":"ssm"},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2511.17599","title":"From Projection to Prediction: Beyond Logits for Scalable Language Models","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2511.20849","title":"Length-MAX Tokenizer for Language Models","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.05988","title":"CyberGFM: Graph Foundation Models for Lateral Movement Detection in Enterprise Networks","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2602.10657","title":"Benchmarks Are Not That Out of Distribution: Word Overlap Predicts Performance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.25800","title":"Barriers to Universal Reasoning With Transformers (And How to Overcome Them)","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2605.13485","title":"Effective Context in Transformers: An Analysis of Fragmentation and Tokenization","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.26444","title":"NanoSpec: Accelerating Speculative Decoding using Minimalist In-Context Vocabularies","created":"2026-04-08","cited_by_count":1,"area":"inference"},{"id":"2608.17286","title":"Abra: Scaling Diffusion Image Training","created":"2026-08-18","cited_by_count":1,"area":"diffusion"},{"id":"2609.31291","title":"Softmax Reparameterization for Output-Head Quantization","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2509.06836","title":"COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2512.13298","title":"MiniLingua: A Small Open-Source LLM for European Languages","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.02867","title":"Training Language Models with homotokens Leads to Delayed Overfitting","created":"2026-01-06","cited_by_count":0,"area":null}],"next_cursor":"100"}