{"total":52,"rows":[{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"area":"lr"},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2511.07384","title":"Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence","created":"2025-11-10","cited_by_count":47,"area":"lr"},{"id":"2412.13795","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","created":"2024-12-18","cited_by_count":37,"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":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31,"area":"moe"},{"id":"2501.06842","title":"SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training","created":"2025-01-12","cited_by_count":28,"area":null},{"id":"2505.11497","title":"QVGen: Pushing the Limit of Quantized Video Generative Models","created":"2025-05-16","cited_by_count":22,"area":"diffusion"},{"id":"2402.02098","title":"Self-attention Networks Localize When QK-eigenspectrum Concentrates","created":"2024-02-03","cited_by_count":19,"area":null},{"id":"2510.02091","title":"Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2601.21204","title":"Scaling Embeddings Outperforms Scaling Experts in Language Models","created":"2026-01-29","cited_by_count":15,"area":"moe"},{"id":"2602.17004","title":"Arcee Trinity Large Technical Report","created":"2026-02-19","cited_by_count":11,"area":"moe"},{"id":"2504.02507","title":"ZClip: Adaptive Spike Mitigation for LLM Pre-Training","created":"2025-04-03","cited_by_count":10,"area":null},{"id":"2404.10630","title":"HLAT: High-quality Large Language Model Pre-trained on AWS Trainium","created":"2024-04-16","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":"2505.11840","title":"On the $O(\\frac{\\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\\ell_1$ Norm","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","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":"2502.17055","title":"GradientStabilizer:Fix the Norm, Not the Gradient","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2507.08472","title":"Pre-Training LLMs on a budget: A comparison of three optimizers","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2510.22228","title":"When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs","created":"2025-10-25","cited_by_count":5,"area":"lr"},{"id":"2410.05052","title":"Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2510.04848","title":"Instability in Downstream Task Performance During LLM Pretraining","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2601.02031","title":"Output Embedding Centering for Stable LLM Pretraining","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.25704","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2511.21377","title":"Controlling changes to attention logits","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2506.22049","title":"GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2510.04202","title":"Spectral Alignment as Predictor of Loss Explosion in Neural Network Training","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2601.22580","title":"SpanNorm: Reconciling Training Stability and Performance in Deep Transformers","created":"2026-01-30","cited_by_count":2,"area":"moe"},{"id":"2605.17787","title":"Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning Rates","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.28116","title":"Mechanism-Driven Monitors for Preemptive Detection of LLM Training Instability","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2410.24050","title":"A Mechanistic Study of Transformers Training Dynamics","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2510.02297","title":"Interactive Training: Feedback-Driven Neural Network Optimization","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2510.23052","title":"Knocking-Heads Attention","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.16956","title":"DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2601.22095","title":"GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2412.16423","title":"Technical Report: Small Language Model for Japanese Clinical and Medicine","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2503.02147","title":"Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2601.11864","title":"AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2605.06169","title":"Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers","created":"2026-05-07","cited_by_count":0,"area":"diffusion"},{"id":"2605.19008","title":"Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.00539","title":"GNMR: Runtime Stability Control for Low-Precision Large Language Model Training","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.19378","title":"Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.34681","title":"SOLAR: A State-Driven Online Learning Rate Scheduler for LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13524","title":"Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}