No article text was recorded for this version.
activation quantization gap
Version 2 of 2335 papers350 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Memory Efficient Tabular Foundation Models
- Blog: Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
- Blog: Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bitwise Regularization
- Blog: From Hashing to CNNs: Training Binary Weight Networks via Hashing
- Blog: Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization
- Blog: BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
- Blog: Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
- Blog: GPTQT: Quantize Large Language Models Twice to Push the Efficiency
- Blog: BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
- Blog: Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights
- Blog: End-To-End Learned Image Compression With Fixed Point Weight Quantization
- Blog: ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning
- Blog: SplitQuantV2: Enhancing Low-Bit Quantization of LLMs Without GPUs
- Blog: Sensitivity-Aware Post-Training Quantization for Deep Neural Networks
- Blog: Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View
- Blog: Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation
- Blog: FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
- Blog: DeepTwist: Learning Model Compression via Occasional Weight Distortion
- Blog: Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks Quantization
- Blog: Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
- Blog: Quantitative Analysis of Performance Drop in DeepSeek Model Quantization
- Blog: FBQuant: FeedBack Quantization for Large Language Models
- Blog: Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization
- Blog: One Weight Bitwidth to Rule Them All
- Blog: QBB: Quantization with Binary Bases for LLMs
- Blog: AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization
- Blog: ICQuant: Index Coding enables Low-bit LLM Quantization
- Blog: Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
- Blog: Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark
- Blog: XTC: Extreme Compression for Pre-trained Transformers Made Simple and Efficient
- Blog: Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs
- Blog: QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- Blog: Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models
- Blog: Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production
- Blog: Treasures in Discarded Weights for LLM Quantization
- Blog: Boolean Logic as an Error feedback mechanism
- Blog: Position-based Scaled Gradient for Model Quantization and Sparse Training
- Blog: AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
- Blog: Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
- Blog: OPTQ: Accurate Quantization for Generative Pre-trained Transformers
- Blog: Scaling Laws for Task-Stratified Knowledge in Post-Training Quantized Large Language Models
- Blog: Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
- Blog: Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
- Blog: MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference
- Blog: ARB-LLM: Alternating Refined Binarizations for Large Language Models
- Blog: Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training
- Blog: QEBVerif: Quantization Error Bound Verification of Neural Networks
- Blog: BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
- Blog: Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models
- Blog: BayesQ: Uncertainty-Guided Bayesian Quantization
- Blog: PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling
- Blog: Radio: Rate–Distortion Optimization for Large Language Model Compression
- Blog: One Weight Bitwidth to Rule Them All
- Blog: Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
- Blog: Towards Efficient and Accurate Winograd Convolution via Full Quantization
- Blog: VQ4ALL: Efficient Neural Network Representation via a Universal Codebook
- Blog: Highly Efficient and Effective LLMs with Multi-Boolean Architectures
- Blog: Low-Rank Correction for Quantized LLMs
- Blog: ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba
- Blog: Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition
Showing 60 of 335 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_activation_quantization_gap_1c631d05,
title = {activation quantization gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/activation-quantization-gap/rdr_1c631d05926a4ea5bcad8141f6484888},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_activation_quantization_gap_1c631d05_v2,
title = {activation quantization gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/activation-quantization-gap/rdr_1c631d05926a4ea5bcad8141f6484888/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}