No article text was recorded for this version.
sparse architecture quantization
Version 1 of 116 papers16 conceptsfrozen 2026-10-04
Papers in this version
- Blog: QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- Blog: Treasures in Discarded Weights for LLM Quantization
- Blog: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
- Blog: QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
- Blog: Float8@2bits: Entropy Coding Enables Data-Free Model Compression
- Blog: ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
- Blog: NIRVANA: Structured pruning reimagined for large language models compression
- Blog: Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
- Blog: HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
- Blog: FPTQuant: Function-Preserving Transforms for LLM Quantization
- Blog: TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
- Blog: TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
- Blog: Training Dynamics Impact Post-Training Quantization Robustness
- Blog: HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
- Blog: Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment
- Blog: Low-Bit Quantization Favors Undertrained LLMs
History & citation
Current · Permanent link
- This direction split from Low-Bit Quantization for Dense and Mixture of Experts Models (81% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sparse_architecture_quantization_3a43beda,
title = {sparse architecture quantization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-architecture-quantization/rdr_3a43bedad9d9463b90613f7b9b480bbb},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_sparse_architecture_quantization_3a43beda_v1,
title = {sparse architecture quantization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-architecture-quantization/rdr_3a43bedad9d9463b90613f7b9b480bbb/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}