{"total":77,"rows":[{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160,"area":"inference"},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2409.12517","title":"Scaling FP8 training to trillion-token LLMs","created":"2024-09-19","cited_by_count":65,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2506.07530","title":"BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation","created":"2025-06-09","cited_by_count":43,"area":"vla"},{"id":"2505.19115","title":"FP4 All the Way: Fully Quantized Training of LLMs","created":"2025-05-25","cited_by_count":40,"area":null},{"id":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2505.11432","title":"MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production","created":"2025-05-16","cited_by_count":31,"area":"moe"},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27,"area":"inference"},{"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":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21,"area":null},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2408.08310","title":"ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws","created":"2024-08-15","cited_by_count":15,"area":null},{"id":"2501.02625","title":"HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs","created":"2025-01-05","cited_by_count":15,"area":null},{"id":"2410.15526","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2601.18150","title":"FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning","created":"2026-01-26","cited_by_count":13,"area":"inference"},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2505.20524","title":"Towards Fully FP8 GEMM LLM Training at Scale","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2509.00404","title":"Metis: Training LLMs with FP4 Quantization","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2501.02423","title":"Scaling Laws for Floating Point Quantization Training","created":"2025-01-05","cited_by_count":8,"area":null},{"id":"2603.00040","title":"Attn-QAT: 4-Bit Attention With Quantization-Aware Training","created":"2026-02-09","cited_by_count":8,"area":null},{"id":"2411.13904","title":"Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning","created":"2024-11-21","cited_by_count":7,"area":"agents"},{"id":"2407.04480","title":"LoCo: Low-Bit Communication Adaptor for Large-scale Model Training","created":"2024-07-05","cited_by_count":6,"area":null},{"id":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5,"area":"moe"},{"id":"2602.23349","title":"FlashOptim: Optimizers for Memory-Efficient Training","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2604.15416","title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2403.20137","title":"Accurate Block Quantization in LLMs with Outliers","created":"2024-03-29","cited_by_count":4,"area":"inference"},{"id":"2407.17353","title":"Scalify: scale propagation for efficient low-precision LLM training","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2409.04833","title":"Achieving Peak Performance for Large Language Models: A Systematic Review","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2507.15465","title":"Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts","created":"2025-07-21","cited_by_count":4,"area":"moe"},{"id":"2509.22935","title":"Compute-Optimal Quantization-Aware Training","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2602.08923","title":"DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2410.03185","title":"EXAQ: Exponent Aware Quantization For LLMs Acceleration","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2503.11486","title":"A Review of DeepSeek Models' Key Innovative Techniques","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2509.22536","title":"A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.13907","title":"AIS: Adaptive Importance Sampling for Quantized RL","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2409.13708","title":"Towards Safe Multilingual Frontier AI","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2506.17768","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2507.10618","title":"Compute Requirements for Algorithmic Innovation in Frontier AI Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2511.05811","title":"MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2511.21910","title":"Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication","created":"2025-11-26","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":"2602.02400","title":"An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.02731","title":"Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs","created":"2026-03-03","cited_by_count":2,"area":"moe"},{"id":"2606.10493","title":"Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design","created":"2026-06-09","cited_by_count":2,"area":"moe"},{"id":"2407.02610","title":"Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2409.04585","title":"CubicML: Automated ML for Large ML Systems Co-design with ML Prediction of Performance","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2506.14435","title":"MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models","created":"2025-06-17","cited_by_count":1,"area":"mllm"},{"id":"2510.08008","title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","created":"2025-10-09","cited_by_count":1,"area":"moe"},{"id":"2510.24061","title":"FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.00874","title":"Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2511.02302","title":"FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error","created":"2025-11-04","cited_by_count":1,"area":"moe"},{"id":"2601.00728","title":"Precision autotuning for linear solvers via contextual bandit-based RL","created":"2026-01-02","cited_by_count":1,"area":"deeprl"},{"id":"2602.02707","title":"Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2508.07142","title":"Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?","created":"2025-08-10","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":"2605.00539","title":"AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.26189","title":"Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training","created":"2026-05-25","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":"2607.07494","title":"GeoFP8: Geometry-Aware FP8 Gradient Compression for Distributed LLM Training","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.09800","title":"Auditing Invisible Weight Updates with Reference Traces","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.26581","title":"Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2609.33591","title":"Pretraining Transformers with Quantized Softmax in Attention","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35392","title":"The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37852","title":"Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39813","title":"Backward-State Policy Is Part of the Learning Algorithm","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}