🎯 Post-training quantization

The items that name it 8

• A Unified Hessian-Guided Framework for Post-Training Quantization
  paper2026-10-29

  Low-bit quantization of large language models after training to reduce memory footprint and computational cost. The page frames accuracy at low precision as depending on quantization ranges, linear transformations and weight rounding.

• Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models
  paper2026-10-28It is written here as Post-training quantization (PTQ).

  Reduces the memory footprint of vision-language-action models after training, though keeping task performance at lower bit widths is hard.

• AxisQ: Depth-Adaptive Channel--Frequency Quantization for Camouflaged Object Detection
  paper2026-10-27It is written here as Post-training quantization (PTQ).

  PTQ

• MPQ: A Message-Passing View of Post-Training Quantization
  paper2026-10-23It is written here as Post-training quantization (PTQ).

  PTQ

• Evaluating the Applicability of LLM Inference Optimizations on Apple Silicon
  paper2026-10-22
• Beyond 4 bits: Data-Centric Post-training Quantization and Recovery
  paper2026-10-20It is written here as Post-training quantization (PTQ).

  PTQ

• Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
  paper2026-10-06
• DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
  paper2026-09-25It is written here as Post-training quantization (AWQ, GPTQ).

  AWQ, GPTQ