{"total":60,"rows":[{"id":"2512.20856","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","created":"2025-12-24","cited_by_count":65,"area":null},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","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":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"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":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11,"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":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","cited_by_count":8,"area":null},{"id":"2511.13061","title":"MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity","created":"2025-11-17","cited_by_count":6,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","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":"2605.09825","title":"Pretraining large language models with MXFP4 on Native FP4 Hardware","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2603.22370","title":"FAAR: Format-Aware Adaptive Rounding for NVFP4","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2605.12245","title":"SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2607.24953","title":"Stable FP4 Training via Transposition-Invariant Block Quantization","created":"2026-07-27","cited_by_count":3,"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":"2602.01410","title":"SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2603.08747","title":"Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.12798","title":"VFA: Relieving Vector Operations in Flash Attention with Global Maximum Pre-computation","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2605.06067","title":"Normalized Architectures are Natively 4-Bit","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.07618","title":"ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2609.02846","title":"UE5M3 FP4 Block Scaling for Stable Language Model Pretraining","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2609.04098","title":"Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2511.19705","title":"CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.02071","title":"BAPS: A Fine-Grained Low-Precision Scheme for Softmax in Attention via Block-Aware Precision reScaling","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.05790","title":"Price of metric universality in vector quantization is at most 0.11 bit","created":"2026-02-05","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":"2605.20402","title":"Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.20799","title":"Instant GPU Efficiency Visibility at Fleet Scale","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.00703","title":"Information-Theoretic Lower Bounds for Bit-Constrained Stochastic Optimization via a Reduction to Compressed Gaussian Mean Estimation","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.06510","title":"FP8 is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail (Sep 3rd version)","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.23419","title":"GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.02893","title":"Variable Bit-width Quantization: Learning Per-Group Precision for \"Bigger-but-Smaller\" Language Models","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2609.39223","title":"QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2512.22804","title":"MoR: Mixture Of Representations For Mixed-Precision Training","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2602.00165","title":"Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.06183","title":"To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.16855","title":"When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.00519","title":"Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade LLM Inference","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.07662","title":"Direction-Preserving Number Representations","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08565","title":"Finer is Better (with the Right Scaling)","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.27616","title":"Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation","created":"2026-05-26","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":"2607.29397","title":"Studying quantization trade-offs for efficient inference deployment in machine translation","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.25188","title":"Transforms for LLM Quantization: The Great Inversion and Format Co-Design","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.00066","title":"OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.08135","title":"KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.28358","title":"MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.36654","title":"Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference","created":"2026-09-29","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":"2609.39111","title":"Bongard: Training Machine Intuition","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00053","title":"Format-Aware Fusion for Fast FP4 Pretraining","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.01889","title":"Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.09183","title":"Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.14277","title":"Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17637","title":"Mixed Precision Scaling Laws for Quantized Pretraining","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}