{"total":152,"rows":[{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2405.04532","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","created":"2024-05-07","cited_by_count":208,"area":"inference"},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170,"area":"diffusion"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2505.11594","title":"SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training","created":"2025-05-16","cited_by_count":66,"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":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41,"area":null},{"id":"2505.19115","title":"FP4 All the Way: Fully Quantized Training of LLMs","created":"2025-05-25","cited_by_count":40,"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":"2605.18739","title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","created":"2026-05-18","cited_by_count":30,"area":"diffusion"},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"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":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2502.20853","title":"Oscillation-Reduced MXFP4 Training for Vision Transformers","created":"2025-02-28","cited_by_count":21,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19,"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":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2510.25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats","created":"2025-10-29","cited_by_count":18,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"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":"2408.00462","title":"Designing Efficient LLM Accelerators for Edge Devices","created":"2024-08-01","cited_by_count":13,"area":null},{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2501.01144","title":"BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference","created":"2025-01-02","cited_by_count":11,"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":"2505.18659","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","created":"2025-05-24","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":"2510.14557","title":"MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving","created":"2025-10-16","cited_by_count":11,"area":"inference"},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11,"area":null},{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","cited_by_count":9,"area":null},{"id":"2509.00404","title":"Metis: Training LLMs with FP4 Quantization","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2601.19026","title":"Is Finer Better? The Limits of Microscaling Formats in Large Language Models","created":"2026-01-26","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":"2409.16626","title":"Ascend HiFloat8 Format for Deep Learning","created":"2024-09-25","cited_by_count":7,"area":null},{"id":"2508.00904","title":"Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2601.22709","title":"Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs","created":"2026-01-30","cited_by_count":6,"area":"mllm"},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2411.18065","title":"FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2503.17513","title":"Improving Quantization with Post-Training Model Expansion","created":"2025-03-21","cited_by_count":5,"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":"2604.08826","title":"HiFloat4 Format for Language Model Pre-training on Ascend NPUs","created":"2026-04-09","cited_by_count":5,"area":"moe"},{"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":"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":"2409.05902","title":"OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2410.10714","title":"SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators","created":"2024-10-14","cited_by_count":4,"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":"2602.08923","title":"DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce","created":"2026-02-09","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":"2501.15448","title":"SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity","created":"2025-01-26","cited_by_count":3,"area":"diffusion"},{"id":"2504.12984","title":"Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2601.20706","title":"NPU Design for Diffusion Language Model Inference","created":"2026-01-28","cited_by_count":3,"area":"diffusion"},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.19561","title":"TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.04115","title":"dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.15682","title":"ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training","created":"2026-06-14","cited_by_count":3,"area":"lr"},{"id":"2607.24953","title":"Stable FP4 Training via Transposition-Invariant Block Quantization","created":"2026-07-27","cited_by_count":3,"area":null},{"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":"2508.04405","title":"FlexQ: Efficient Post-training INT6 Quantization for LLM Serving via Algorithm-System Co-Design","created":"2025-08-06","cited_by_count":2,"area":"inference"},{"id":"2512.15306","title":"LLMQ: Efficient Lower-Precision Pretraining for Consumer GPUs","created":"2025-12-17","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":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2602.18851","title":"Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2605.12327","title":"Grid Games: The Power of Multiple Grids for Quantizing Large Language Models","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.20381","title":"Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe","created":"2026-06-18","cited_by_count":2,"area":"lr"},{"id":"2606.23406","title":"HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models","created":"2026-06-22","cited_by_count":2,"area":"diffusion"},{"id":"2607.16237","title":"Quantizing Recursive Reasoning Models","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2607.24377","title":"MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention","created":"2026-07-27","cited_by_count":2,"area":"diffusion"},{"id":"2608.01847","title":"FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.13756","title":"The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference","created":"2026-08-13","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":"2311.05034","title":"Just-in-time Quantization with Processing-In-Memory for Efficient ML Training","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2502.17728","title":"LLM Inference Acceleration via Efficient Operation Fusion","created":"2025-02-24","cited_by_count":1,"area":"inference"},{"id":"2505.12988","title":"Optimal Formats for Weight Quantisation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.13159","title":"MXDOTP: A RISC-V ISA Extension for Enabling Microscaling (MX) Floating-Point Dot Products","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.16335","title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2508.21394","title":"AI Compute Architecture and Evolution Trends","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2512.09202","title":"Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2512.12930","title":"SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.20115","title":"How Much Progress Has There Been in NVIDIA Datacenter GPUs?","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2604.00529","title":"MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.03950","title":"Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2604.04523","title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.12782","title":"OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension","created":"2026-04-14","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":"2607.05711","title":"FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models","created":"2026-07-07","cited_by_count":1,"area":"diffusion"},{"id":"2607.17733","title":"MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference","created":"2026-07-20","cited_by_count":1,"area":"inference"},{"id":"2607.20518","title":"CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits","created":"2026-07-08","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":"2609.03807","title":"Almost Free State Prediction Separation","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2609.04526","title":"Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2407.01475","title":"Exploring FPGA designs for MX and beyond","created":"2024-07-01","cited_by_count":0,"area":null}],"next_cursor":"100"}