{"total":35,"rows":[{"id":"2507.16099","title":"TorchAO: PyTorch-Native Training-to-Serving Model Optimization","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2605.22064","title":"Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild","created":"2026-05-21","cited_by_count":10,"area":null},{"id":"2509.23809","title":"Tequila: Trapping-free Ternary Quantization for Large Language Models","created":"2025-09-28","cited_by_count":9,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2603.04956","title":"WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization","created":"2026-03-05","cited_by_count":7,"area":null},{"id":"2503.17513","title":"Improving Quantization with Post-Training Model Expansion","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2506.01863","title":"Unified Scaling Laws for Compressed Representations","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2508.05571","title":"iFairy: the First 2-bit Complex LLM with All Parameters in $\\{\\pm1, \\pm i\\}$","created":"2025-08-07","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":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2606.10531","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2606.10890","title":"Optimal Post-Training Quantization Scales and Where to Find Them","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2512.06443","title":"Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2601.19320","title":"StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.25469","title":"JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2505.08620","title":"Resource-Efficient Language Models: Quantization for Fast and Accessible Inference","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2602.01027","title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.15563","title":"1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.01599","title":"Boosting Entropy with Bell Box Quantization","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2606.09012","title":"Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin","created":"2026-06-08","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":"2609.16338","title":"Breaking the 1.58-bit Barrier for Ternary LLMs","created":"2026-09-14","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":"2601.20745","title":"HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2608.08188","title":"Quantization Degradation in Large Language Models: A Signal-Noise Perspective","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.26333","title":"Disaggregated Quantization: Specializing LLM Prefill and Decode","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.32659","title":"Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32902","title":"Linger and Lose: Knowledge Collapse in Low-Bit Language Models","created":"2026-09-26","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":"2610.14745","title":"SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}