{"total":13,"rows":[{"id":"2501.13987","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","created":"2025-01-23","cited_by_count":97,"area":null},{"id":"2502.16473","title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2511.21513","title":"IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2605.19561","title":"TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2510.01240","title":"RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2605.24144","title":"EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2504.17132","title":"Latent Video Dataset Distillation","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2509.02411","title":"A Survey: Towards Privacy and Security in Mobile Large Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2511.15369","title":"IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2604.04523","title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2607.23390","title":"When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2604.25306","title":"QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2607.03057","title":"LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression","created":"2026-07-03","cited_by_count":0,"area":null}],"next_cursor":null}