No article text was recorded for this version.
mixed-precision quantization
Version 1 of 1470 papers611 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Super-Resolution Model Quantized in Multi-Precision
- Blog: Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
- Blog: DynaMIX: Resource Optimization for DNN-Based Real-Time Applications on a Multi-Tasking System
- Blog: Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model
- Blog: Mixed Precision DNN Quantization for Overlapped Speech Separation and Recognition
- Blog: MoQa: Rethinking MoE Quantization with Multi-stage Data-model Distribution Awareness
- Blog: End-to-end codesign of Hessian-aware quantized neural networks for FPGAs
- Blog: Post-training Quantization with Progressive Calibration and Activation Relaxing for Text-to-Image Diffusion Models
- Blog: Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
- Blog: Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml
- Blog: Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
- Blog: Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
- Blog: EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices
- Blog: Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes
- Blog: Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
- Blog: Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark
- Blog: Nearly Lossless Adaptive Bit Switching
- Blog: Collaborative Compression for Large-Scale MoE Deployment on Edge
- Blog: Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
- Blog: Post-Training Quantization for Vision Transformer
- Blog: Mixture Compressor for Mixture-of-Experts LLMs Gains More
- Blog: Gradient-Based Post-Training Quantization: Challenging the Status Quo
- Blog: A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation
- Blog: Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Switchboard Corpus
- Blog: Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization
- Blog: Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems
- Blog: EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models
- Blog: Editorial: 2020 India international congress on computational intelligence
- Blog: EQO: Exploring Ultra-Efficient Private Inference with Winograd-Based Protocol and Quantization Co-Optimization
- Blog: You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
- Blog: Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge
- Blog: AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization
- Blog: ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization
- Blog: Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
- Blog: YolactEdge: Real-time Instance Segmentation on the Edge
- Blog: CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
- Blog: GenPTQ: Green Post-Training Quantization for Large-Scale ASR Models with Mixed-Precision Bit Allocation
- Blog: Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees
- Blog: Extremely Low Footprint End-to-End ASR System for Smart Device
- Blog: VaPr: Variable-Precision Tensors to Accelerate Robot Motion Planning
- Blog: COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
- Blog: Nearly Lossless Adaptive Bit Switching
- Blog: Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA
- Blog: MKQ-BERT: Quantized BERT with 4-bits Weights and Activations
- Blog: LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
- Blog: QPyTorch: A Low-Precision Arithmetic Simulation Framework
- Blog: Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
- Blog: Differentiable Fine-grained Quantization for Deep Neural Network Compression
- Blog: Fixed Point Quantization of Deep Convolutional Networks
- Blog: CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
- Blog: 4-bit Conformer with Native Quantization Aware Training for Speech Recognition
- Blog: TurboAttention: Efficient attention approximation for high throughputs llm
- Blog: PCA-driven Hybrid network design for enabling Intelligence at the Edge
- Blog: GWQ: Gradient-Aware Weight Quantization for Large Language Models
- Blog: QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
- Blog: QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
- Blog: Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Swithboard Corpus
- Blog: SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
- Blog: MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective
- Blog: FracBits: Mixed Precision Quantization via Fractional Bit-Widths
Showing 60 of 470 papers.
History & citation
Current · Permanent link
- Hessian Aware Mixed Precision Quantization merged into this direction (58% overlap)
- Heterogeneous Quantization for Efficient Neural Networks merged into this direction (91% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_mixed_precision_quantization_539353bb,
title = {mixed-precision quantization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mixed-precision-quantization/rdr_539353bbabf1425b9c5ed42d5ade6338},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_mixed_precision_quantization_539353bb_v1,
title = {mixed-precision quantization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mixed-precision-quantization/rdr_539353bbabf1425b9c5ed42d5ade6338/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}