{"total":421,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"area":null},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2409.16235","title":"EuroLLM: Multilingual Language Models for Europe","created":"2024-09-24","cited_by_count":106,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2406.04485","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","created":"2024-06-06","cited_by_count":82,"area":null},{"id":"2510.21585","title":"REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects","created":"2025-10-24","cited_by_count":80,"area":null},{"id":"2509.25149","title":"Pretraining Large Language Models with NVFP4","created":"2025-09-29","cited_by_count":76,"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":"2407.07263","title":"Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models","created":"2024-07-09","cited_by_count":72,"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":"2505.14766","title":"This Time is Different: An Observability Perspective on Time Series Foundation Models","created":"2025-05-20","cited_by_count":68,"area":null},{"id":"2405.19327","title":"MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series","created":"2024-05-29","cited_by_count":67,"area":null},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67,"area":null},{"id":"2504.13161","title":"Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training","created":"2025-04-17","cited_by_count":66,"area":null},{"id":"2603.15031","title":"Attention Residuals","created":"2026-03-16","cited_by_count":65,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2602.06053","title":"PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models","created":"2026-01-14","cited_by_count":63,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2412.04506","title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise","created":"2024-12-03","cited_by_count":58,"area":null},{"id":"2504.08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","created":"2025-04-11","cited_by_count":57,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"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":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2505.18022","title":"RemoteSAM: Towards Segment Anything for Earth Observation","created":"2025-05-23","cited_by_count":39,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2505.05427","title":"Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data","created":"2025-05-08","cited_by_count":38,"area":null},{"id":"2409.17115","title":"Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale","created":"2024-09-25","cited_by_count":37,"area":null},{"id":"2409.18071","title":"FreeEdit: Mask-free Reference-based Image Editing with Multi-modal Instruction","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2502.06042","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","created":"2025-02-09","cited_by_count":35,"area":null},{"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":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"area":null},{"id":"2409.09811","title":"PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics","created":"2024-09-15","cited_by_count":34,"area":null},{"id":"2503.04715","title":"Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining","created":"2025-03-06","cited_by_count":34,"area":null},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34,"area":null},{"id":"2501.18965","title":"The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training","created":"2025-01-31","cited_by_count":33,"area":null},{"id":"2407.12874","title":"SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning","created":"2024-07-16","cited_by_count":32,"area":null},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2509.24663","title":"InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation","created":"2025-09-29","cited_by_count":32,"area":null},{"id":"2503.05500","title":"EuroBERT: Scaling Multilingual Encoders for European Languages","created":"2025-03-07","cited_by_count":31,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2605.20119","title":"Toto 2.0: Time Series Forecasting Enters the Scaling Era","created":"2026-05-19","cited_by_count":30,"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":"2408.11029","title":"Scaling Law with Learning Rate Annealing","created":"2024-08-20","cited_by_count":29,"area":null},{"id":"2408.12171","title":"Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey","created":"2024-08-22","cited_by_count":28,"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":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2406.15718","title":"Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models","created":"2024-06-22","cited_by_count":26,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2505.13077","title":"Advancing Sequential Numerical Prediction in Autoregressive Models","created":"2025-05-19","cited_by_count":26,"area":null},{"id":"2404.07584","title":"UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs","created":"2024-04-11","cited_by_count":24,"area":null},{"id":"2607.05722","title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","created":"2026-07-07","cited_by_count":24,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2408.04585","title":"Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness","created":"2024-08-08","cited_by_count":22,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2412.01505","title":"Scaling Law for Language Models Training Considering Batch Size","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2502.01715","title":"Process-Supervised Reinforcement Learning for Code Generation","created":"2025-02-03","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2504.05747","title":"SEA-LION: Southeast Asian Languages in One Network","created":"2025-04-08","cited_by_count":22,"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":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2601.22813","title":"Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation","created":"2026-01-30","cited_by_count":21,"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":"2510.19178","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","created":"2025-10-22","cited_by_count":20,"area":null},{"id":"2404.14688","title":"FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model","created":"2024-04-23","cited_by_count":19,"area":null},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19,"area":null},{"id":"2407.15240","title":"BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models","created":"2024-07-21","cited_by_count":18,"area":null},{"id":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2501.18972","title":"BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics","created":"2025-01-31","cited_by_count":18,"area":null},{"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":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2601.22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","created":"2026-01-29","cited_by_count":18,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2411.13610","title":"Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization","created":"2024-11-20","cited_by_count":17,"area":null}],"next_cursor":"100"}