{"total":28,"rows":[{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"area":null},{"id":"2507.18553","title":"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm","created":"2025-07-24","cited_by_count":20,"area":null},{"id":"2512.00956","title":"WUSH: Near-Optimal Adaptive Transforms for LLM Quantization","created":"2025-11-30","cited_by_count":15,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2601.09555","title":"Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats","created":"2026-01-14","cited_by_count":10,"area":null},{"id":"2605.19537","title":"The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2602.10144","title":"When LLMs get significantly worse: A statistical approach to detect model degradations","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2505.22945","title":"OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2511.22334","title":"Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2607.08734","title":"The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2602.03537","title":"MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2606.14516","title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2606.19558","title":"Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2503.16505","title":"Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2601.22787","title":"Float8@2bits: Entropy Coding Enables Data-Free Model Compression","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.14591","title":"FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2609.10494","title":"IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2609.10550","title":"Optimizing AI Inference Across the Deployment Stack","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2512.19305","title":"CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2604.19167","title":"LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.19645","title":"K-Quantization and its Impact on Output Performance","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2609.13031","title":"Attention Quantization for Tabular Foundation Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.32890","title":"A Function-Level Vulnerability Score Measures Flag Rate More Than the Model: Protocol Effects on Paired Benchmarks","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36437","title":"Bits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00694","title":"How Divergence Becomes Decision Flips in Compressed Language Models","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}