{"total":183,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927,"area":null},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864,"area":"wm"},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752,"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":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480,"area":"lr"},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294,"area":null},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232,"area":"mllm"},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202,"area":null},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192,"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":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","created":"2024-02-27","cited_by_count":90,"area":null},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89,"area":"lr"},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2409.19606","title":"Hyper-Connections","created":"2024-09-29","cited_by_count":84,"area":null},{"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":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"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":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2503.00710","title":"Proteina: Scaling Flow-based Protein Structure Generative Models","created":"2025-03-02","cited_by_count":65,"area":null},{"id":"2407.01800","title":"Normalization and effective learning rates in reinforcement learning","created":"2024-07-01","cited_by_count":58,"area":"deeprl"},{"id":"2312.16903","title":"Spike No More: Stabilizing the Pre-training of Large Language Models","created":"2023-12-28","cited_by_count":52,"area":null},{"id":"2501.12370","title":"Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models","created":"2025-01-21","cited_by_count":50,"area":"moe"},{"id":"2503.20853","title":"Unified Multimodal Discrete Diffusion","created":"2025-03-26","cited_by_count":49,"area":"diffusion"},{"id":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46,"area":"ssm"},{"id":"2410.08184","title":"Scaling Laws For Diffusion Transformers","created":"2024-10-10","cited_by_count":44,"area":"diffusion"},{"id":"2405.13698","title":"How to set AdamW's weight decay as you scale model and dataset size","created":"2024-05-22","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":"2409.12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","created":"2024-09-19","cited_by_count":42,"area":"synth"},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41,"area":null},{"id":"2409.19913","title":"Scaling Optimal LR Across Token Horizons","created":"2024-09-30","cited_by_count":40,"area":null},{"id":"2505.12082","title":"Model Merging in Pre-training of Large Language Models","created":"2025-05-17","cited_by_count":37,"area":"moe"},{"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":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2404.14408","title":"SpaceByte: Towards Deleting Tokenization from Large Language Modeling","created":"2024-04-22","cited_by_count":34,"area":null},{"id":"2502.02732","title":"Peri-LN: Revisiting Normalization Layer in the Transformer Architecture","created":"2025-02-04","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":"2311.14495","title":"StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization","created":"2023-11-24","cited_by_count":30,"area":null},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29,"area":"deeprl"},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","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":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2407.21075","title":"Apple Intelligence Foundation Language Models","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2409.15156","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","created":"2024-09-23","cited_by_count":23,"area":"lr"},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","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":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2406.10670","title":"CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training","created":"2024-06-15","cited_by_count":20,"area":null},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","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":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2602.04029","title":"PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models","created":"2026-02-03","cited_by_count":19,"area":"synth"},{"id":"2405.12807","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15,"area":null},{"id":"2404.09841","title":"Anatomy of Industrial Scale Multilingual ASR","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2405.13218","title":"Computational Tradeoffs in Image Synthesis: Diffusion, Masked-Token, and Next-Token Prediction","created":"2024-05-21","cited_by_count":13,"area":null},{"id":"2410.16682","title":"Methods of improving LLM training stability","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2504.13292","title":"Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model","created":"2025-04-17","cited_by_count":13,"area":null},{"id":"2404.17785","title":"Temporal Scaling Law for Large Language Models","created":"2024-04-27","cited_by_count":11,"area":null},{"id":"2406.16508","title":"Large Vocabulary Size Improves Large Language Models","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2405.18710","title":"To FP8 and Back Again: Quantifying Reduced Precision Effects on LLM Training Stability","created":"2024-05-29","cited_by_count":9,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","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":"2510.22026","title":"Normalization in Attention Dynamics","created":"2025-10-24","cited_by_count":9,"area":null},{"id":"2602.01439","title":"TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse","created":"2026-02-01","cited_by_count":9,"area":"deeprl"},{"id":"2407.06183","title":"Stepping on the Edge: Curvature Aware Learning Rate Tuners","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2505.13791","title":"Scalable Autoregressive 3D Molecule Generation","created":"2025-05-20","cited_by_count":8,"area":"diffusion"},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8,"area":null},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"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":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2502.11034","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","created":"2025-02-16","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":"2505.22014","title":"Learning in Compact Spaces with Approximately Normalized Transformer","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2509.09009","title":"Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2512.08894","title":"Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training","created":"2025-12-09","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":"2602.21472","title":"The Design Space of Tri-Modal Masked Diffusion Models","created":"2026-02-25","cited_by_count":6,"area":"diffusion"},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2607.20548","title":"SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales","created":"2026-07-13","cited_by_count":6,"area":null},{"id":"2402.10202","title":"Bridging Associative Memory and Probabilistic Modeling","created":"2024-02-15","cited_by_count":5,"area":null}],"next_cursor":"100"}