{"total":47,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2408.00738","title":"Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology","created":"2024-08-01","cited_by_count":161,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2306.02602","title":"ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction","created":"2023-06-05","cited_by_count":63,"area":null},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56,"area":null},{"id":"2309.15564","title":"Jointly Training Large Autoregressive Multimodal Models","created":"2023-09-27","cited_by_count":32,"area":null},{"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":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20,"area":null},{"id":"2410.16682","title":"Methods of improving LLM training stability","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2506.04805","title":"Adaptive Preconditioners Trigger Loss Spikes in Adam","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2309.03450","title":"XGen-7B Technical Report","created":"2023-09-07","cited_by_count":12,"area":null},{"id":"2407.14885","title":"Falcon2-11B Technical Report","created":"2024-07-20","cited_by_count":12,"area":null},{"id":"2405.02803","title":"Is Flash Attention Stable?","created":"2024-05-05","cited_by_count":10,"area":null},{"id":"2502.20566","title":"Stochastic Rounding for LLM Training: Theory and Practice","created":"2025-02-27","cited_by_count":10,"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":"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":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2505.16363","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2408.09598","title":"Anytime-Valid Inference for Double/Debiased Machine Learning of Causal Parameters","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2605.06152","title":"Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes","created":"2026-05-07","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":"2510.25244","title":"BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2604.00726","title":"Exploring Silent Data Corruption as a Reliability Challenge in LLM Training","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2601.20769","title":"Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidence","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2605.09176","title":"Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2406.09900","title":"GEB-1.3B: Open Lightweight Large Language Model","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2408.12273","title":"Geometrical structures of digital fluctuations in parameter space of neural networks trained with adaptive momentum optimization","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2504.18929","title":"Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2507.06464","title":"SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2607.21005","title":"Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2305.15997","title":"SING: A Plug-and-Play DNN Learning Technique","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2306.09338","title":"Understanding Optimization of Deep Learning via Jacobian Matrix and Lipschitz Constant","created":"2023-06-15","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":"2602.05780","title":"Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.16809","title":"A Mechanism Study of Delayed Loss Spikes in Batch-Normalized Linear Models","created":"2026-04-18","cited_by_count":0,"area":null},{"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":"2606.16768","title":"Taming Curvature: Architecture Warm-Up for Stable Transformer Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.01678","title":"SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.02091","title":"One QK Channel, Many Sources: Tracing Low-Precision Attention Collapse","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.18314","title":"Beyond Quadratic Loss: The Stability Phase Diagram of Adam","created":"2026-09-16","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}