No article text was recorded for this version.
calibration data sensitivity
Version 1 of 1103 papers116 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox
- Blog: Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
- Blog: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
- Blog: MetaAug: Meta-data Augmentation for Post-training Quantization
- Blog: Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
- Blog: Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
- Blog: LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices
- Blog: PD-Quant: Post-Training Quantization based on Prediction Difference Metric
- Blog: Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization
- Blog: XCAT - Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation
- Blog: Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
- Blog: LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
- Blog: FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point
- Blog: Revisiting Large Language Model Pruning using Neuron Semantic Attribution
- Blog: Treasures in Discarded Weights for LLM Quantization
- Blog: HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
- Blog: QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution
- Blog: Delta Decompression for MoE-based LLMs Compression
- Blog: QERA: an Analytical Framework for Quantization Error Reconstruction
- Blog: NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
- Blog: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- Blog: DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
- Blog: LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models
- Blog: You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
- Blog: Radio: Rate–Distortion Optimization for Large Language Model Compression
- Blog: Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs
- Blog: SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization
- Blog: SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
- Blog: ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
- Blog: HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
- Blog: QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
- Blog: CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization
- Blog: LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid
- Blog: LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid
- Blog: Q&C: When Quantization Meets Cache in Efficient Generation
- Blog: Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
- Blog: AE-Qdrop: Towards Accurate and Efficient Low-Bit Post-Training Quantization for A Convolutional Neural Network
- Blog: Progressive Binarization with Semi-Structured Pruning for LLMs
- Blog: QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization
- Blog: QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
- Blog: SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization
- Blog: MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
- Blog: TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
- Blog: A3: an Analytical Low-Rank Approximation Framework for Attention
- Blog: Search for Efficient Large Language Models
- Blog: FlatQuant: Flatness Matters for LLM Quantization
- Blog: Timestep-Aware Correction for Quantized Diffusion Models
- Blog: DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models
- Blog: Efficient Large Language Model Inference with Neural Block Linearization
- Blog: Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression
- Blog: Bit-shrinking: Limiting Instantaneous Sharpness for Improving Post-training Quantization
- Blog: PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
- Blog: Leveraging Inter-Layer Dependency for Post -Training Quantization
- Blog: DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
- Blog: A Case Study of Quantizing Convolutional Neural Networks for Fast Disease Diagnosis on Portable Medical Devices
- Blog: TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction
- Blog: LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
- Blog: Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization
- Blog: Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model
- Blog: ERQ: Error Reduction for Post-Training Quantization of Vision Transformers
Showing 60 of 103 papers.
History & citation
Current · Permanent link
- This direction split from Robust Post Training Quantization for Distribution Shift (61% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_calibration_data_sensitivity_142fde87,
title = {calibration data sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/calibration-data-sensitivity/rdr_142fde87695d4899b20065fc0225902c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_calibration_data_sensitivity_142fde87_v1,
title = {calibration data sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/calibration-data-sensitivity/rdr_142fde87695d4899b20065fc0225902c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}