{"total":58,"rows":[{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2510.16981","title":"MuonBP: Faster Muon via Block-Periodic Orthogonalization","created":"2025-10-19","cited_by_count":35,"area":null},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2507.16099","title":"TorchAO: PyTorch-Native Training-to-Serving Model Optimization","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2504.20966","title":"Softpick: No Attention Sink, No Massive Activations with Rectified Softmax","created":"2025-04-29","cited_by_count":22,"area":null},{"id":"2506.16640","title":"Long-Context Generalization with Sparse Attention","created":"2025-06-19","cited_by_count":21,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2605.20613","title":"HRM-Text: Efficient Pretraining Beyond Scaling","created":"2026-05-20","cited_by_count":9,"area":null},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2411.00284","title":"SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compile","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2412.21124","title":"Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2507.05411","title":"AXLearn: Modular, Hardware-Agnostic Large Model Training","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2511.07464","title":"Motif 2 12.7B technical report","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2604.13327","title":"Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2502.19790","title":"Mixtera: A Data Plane for Foundation Model Training","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2506.06472","title":"Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2604.27077","title":"Learning Rate Transfer in Normalized Transformers","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2606.27153","title":"DMuon: Efficient Distributed Muon Training with Near-Adam Overhead","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2505.11820","title":"Chain-of-Model Learning for Language Model","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2506.09452","title":"Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2512.12131","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2602.08387","title":"Modalities, a PyTorch-native Framework For Large-scale LLM Training and Research","created":"2026-02-09","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":"2605.06546","title":"Efficient Pre-Training with Token Superposition","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2412.14374","title":"Scaling Deep Learning Training with MPMD Pipeline Parallelism","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2505.23523","title":"Efficient AllReduce with Stragglers","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.07003","title":"veScale: Consistent and Efficient Tensor Programming with Eager-Mode SPMD","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2509.19396","title":"OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2602.21196","title":"Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.10886","title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.29157","title":"Parallax: Parameterized Local Linear Attention for Language Modeling","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.13894","title":"Gefen: Optimized Stochastic Optimizer","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2505.01616","title":"Phantora: Maximizing Code Reuse in Simulation-based Machine Learning System Performance Estimation","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.11170","title":"Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2510.02483","title":"Litespark Technical Report: High-Throughput, Energy-Efficient LLM Training Framework","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2511.12500","title":"Iris: First-Class Multi-GPU Programming Experience in Triton","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2512.17570","title":"GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2602.05754","title":"TimelyFreeze: Adaptive Parameter Freezing Mechanism for Pipeline Parallelism","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.02525","title":"AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.21603","title":"DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.23464","title":"Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.11169","title":"Piper: A Programmable Distributed Training System","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.16384","title":"Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.11034","title":"SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-Training","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.23840","title":"ShardMeter: Sharded and Geo-Distributed Training Without the Guesswork","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.08966","title":"Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.19291","title":"Why Pretraining Fails to Share Cross-Lingual Knowledge","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.04518","title":"Length Generalization Needs Proper Regularization","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.10975","title":"Optimizing Large Language Models with Chained LMOs","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}