{"total":23,"rows":[{"id":"2312.17238","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","created":"2023-12-28","cited_by_count":91,"area":"moe"},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"id":"2505.03804","title":"MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance","created":"2025-05-02","cited_by_count":34,"area":"moe"},{"id":"2308.09723","title":"FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs","created":"2023-08-16","cited_by_count":22,"area":"moe"},{"id":"2404.01365","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","created":"2024-04-01","cited_by_count":21,"area":"moe"},{"id":"2503.06881","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","created":"2025-03-10","cited_by_count":12,"area":"moe"},{"id":"2602.08621","title":"Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs","created":"2026-02-09","cited_by_count":9,"area":"moe"},{"id":"2505.11564","title":"HessFormer: Hessians at Foundation Scale","created":"2025-05-16","cited_by_count":4,"area":"moe"},{"id":"2507.15465","title":"Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts","created":"2025-07-21","cited_by_count":4,"area":"moe"},{"id":"2508.16700","title":"GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model","created":"2025-08-22","cited_by_count":2,"area":"moe"},{"id":"2604.10603","title":"MoEITS: A Green AI approach for simplifying MoE-LLMs","created":"2026-04-12","cited_by_count":1,"area":"moe"},{"id":"2508.07329","title":"Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative","created":"2025-08-10","cited_by_count":0,"area":"moe"},{"id":"2602.19938","title":"A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs","created":"2026-02-23","cited_by_count":0,"area":"moe"},{"id":"2603.20492","title":"AE-LLM: Adaptive Efficiency Optimization for Large Language Models","created":"2026-03-20","cited_by_count":0,"area":"moe"},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2605.14844","title":"XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference","created":"2026-05-14","cited_by_count":0,"area":"moe"},{"id":"2605.15572","title":"Measuring Maximum Activations in Open Large Language Models","created":"2026-05-15","cited_by_count":0,"area":"moe"},{"id":"2607.06601","title":"TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2608.06723","title":"Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors","created":"2026-08-07","cited_by_count":0,"area":"moe"},{"id":"2609.12550","title":"Quality-Constrained Routing over a Fixed Pool of Quantized Mixture-of-Experts Instances","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.18131","title":"Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.35883","title":"CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2610.16890","title":"FORGE: Procedural Weight Generation for Sparse MoE Inference","created":"2026-10-12","cited_by_count":0,"area":"moe"}],"next_cursor":null}