{"total":22,"rows":[{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2510.01650","title":"The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM","created":"2025-10-02","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":"2605.08195","title":"ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device","created":"2026-05-05","cited_by_count":5,"area":null},{"id":"2604.08358","title":"Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2602.23128","title":"Bound to Disagree: Generalization Bounds via Certifiable Surrogates","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2604.03420","title":"Zero-Shot Quantization via Weight-Space Arithmetic","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2509.06326","title":"AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs","created":"2025-09-08","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":"2606.23419","title":"GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation","created":"2026-06-22","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":"2603.13180","title":"MXNorm: Reusing MXFP block scales for efficient tensor normalisation","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.21442","title":"torchtune: PyTorch native post-training library","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.21413","title":"CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.18540","title":"Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.18182","title":"Efficient INT8 Inference of Small NLP Models on Server CPUs with PyTorch Native Stack","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.28003","title":"A Method for Layer Bit-Width Allocation in LLM Quantization via Performance Maximization Under a Quality-Degradation Constraint","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.31564","title":"Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34185","title":"EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates","created":"2026-09-28","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":"2610.12444","title":"Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14703","title":"Linear-Time Non-Local Codec Placement for Machine Learning Model Compression","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}