{"total":15,"rows":[{"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":"2608.27168","title":"Magpie: Real-Time World Renderer for Interactive Games","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2605.29128","title":"Apertus LLM Family Expansion via Distillation and Quantization","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.06527","title":"Characterizing the Impact of NVFP4 Quantization for Low-Power Edge AI Deployment","created":"2026-06-03","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":"2605.07662","title":"Direction-Preserving Number Representations","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.10210","title":"Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.21171","title":"FTerViT: Fully Ternary Vision Transformer","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.05682","title":"Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.07098","title":"SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices","created":"2026-06-05","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":"2608.20953","title":"Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs","created":"2026-08-21","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":"2609.36654","title":"Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}