GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
hub
Brecq: Pushing the limit of post-training quantization by block reconstruction.arXiv preprint arXiv:2102.05426
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
CoRa reclaims quantization residuals in pre-trained ConvNets by searching low-rank adapter architectures instead of weights, matching SOTA accuracy on ImageNet in 3-4 bit settings with under 250 iterations on 1600 images.
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
MaskAQ generates synthetic samples for ViT quantization by identifying and selectively aligning sparse informative regions in self-attention maps, combined with periodic sample refreshing.
MCWC aligns permutation-symmetric blocks across layers to enable sequential prediction and residual entropy coding, improving rate-accuracy tradeoffs versus quantization and prior codecs on language and vision models.
GEMQ applies global LP-based expert importance estimation and router fine-tuning within progressive quantization to cut memory and speed inference in MoE LLMs with little accuracy loss.
Nonlinear Bipolar Compensation with Bipolar Logarithmic Transformation reduces outlier effects in post-training quantization by performing compensation in a compressed transformed space.
OSAQ suppresses weight outliers in LLMs via a closed-form additive transformation from the Hessian's stable null space, improving 2-bit quantization perplexity by over 40% versus vanilla GPTQ with no inference overhead.
CoreQ delivers adaptive mismatch correction via closed-form geometric coefficient and successive rounding to improve PTQ accuracy for large language models.
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
AHCQ-SAM introduces ACNR, HLUQ, CAG, and LNQ quantization techniques that deliver 15.2% mAP gain on 4-bit SAM-B and 14.01% J&F gain on 4-bit SAM2-Tiny versus prior PTQ methods.
SAGE-PTQ is a graph-guided ultra-low-bit PTQ framework that achieves 1.03 average weight bits and 0.004 scaling bits per matrix on LLMs while reporting lower perplexity and memory use than BiLLM and PB-LLM.
MARR uses per-module adaptive residual scaling updated by PID feedback to balance error correction against Hessian-approximation bias in low-bit PTQ.
CAR-SAM introduces MatMul-Aware Compensation and Joint Cross-Attention Reconstruction to enable stable 4-bit post-training quantization of SAM, outperforming prior PTQ methods by 14.6% mAP on SAM-B and 6.6% on SAM-L.
With known covariance, waterfilling improves GPTQ and WaterSIC reaches within 0.25 bit/entry of the rate-distortion limit while being basis-independent.
DA-PTQ quantizes VLAs by compensating cross-space distortions and allocating mixed precision to minimize motion errors and kinematic drift in trajectories.
A post-training quantization technique for 1-bit LLMs that corrects layer-wise error accumulation and anisotropic representation distortion to preserve output behavior more effectively than existing methods.
GoQuant formulates quantization as dual-basis geometric projection to create higher-resolution residual lattices for 3-bit PoT transformer quantization using only shift-and-add, reporting 6.10 perplexity on LLaMA-2-7B.
citing papers explorer
-
GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation
GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.
-
Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization
CoRa reclaims quantization residuals in pre-trained ConvNets by searching low-rank adapter architectures instead of weights, matching SOTA accuracy on ImageNet in 3-4 bit settings with under 250 iterations on 1600 images.
-
STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.
-
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
MaskAQ generates synthetic samples for ViT quantization by identifying and selectively aligning sparse informative regions in self-attention maps, combined with periodic sample refreshing.
-
Motion-Compensated Weight Compression
MCWC aligns permutation-symmetric blocks across layers to enable sequential prediction and residual entropy coding, improving rate-accuracy tradeoffs versus quantization and prior codecs on language and vision models.
-
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
GEMQ applies global LP-based expert importance estimation and router fine-tuning within progressive quantization to cut memory and speed inference in MoE LLMs with little accuracy loss.
-
Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
Nonlinear Bipolar Compensation with Bipolar Logarithmic Transformation reduces outlier effects in post-training quantization by performing compensation in a compressed transformed space.
-
OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
OSAQ suppresses weight outliers in LLMs via a closed-form additive transformation from the Hessian's stable null space, improving 2-bit quantization perplexity by over 40% versus vanilla GPTQ with no inference overhead.
-
CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
CoreQ delivers adaptive mismatch correction via closed-form geometric coefficient and successive rounding to improve PTQ accuracy for large language models.
-
Sampling-Aware Quantization for Diffusion Models
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
-
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
AHCQ-SAM introduces ACNR, HLUQ, CAG, and LNQ quantization techniques that deliver 15.2% mAP gain on 4-bit SAM-B and 14.01% J&F gain on 4-bit SAM2-Tiny versus prior PTQ methods.
-
Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models
SAGE-PTQ is a graph-guided ultra-low-bit PTQ framework that achieves 1.03 average weight bits and 0.004 scaling bits per matrix on LLMs while reporting lower perplexity and memory use than BiLLM and PB-LLM.
-
MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
MARR uses per-module adaptive residual scaling updated by PID feedback to balance error correction against Hessian-approximation bias in low-bit PTQ.
-
CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model
CAR-SAM introduces MatMul-Aware Compensation and Joint Cross-Attention Reconstruction to enable stable 4-bit post-training quantization of SAM, outperforming prior PTQ methods by 14.6% mAP on SAM-B and 6.6% on SAM-L.
-
High-Rate Quantized Matrix Multiplication II
With known covariance, waterfilling improves GPTQ and WaterSIC reaches within 0.25 bit/entry of the rate-distortion limit while being basis-independent.
-
DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
DA-PTQ quantizes VLAs by compensating cross-space distortions and allocating mixed precision to minimize motion errors and kinematic drift in trajectories.
-
Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models
A post-training quantization technique for 1-bit LLMs that corrects layer-wise error accumulation and anisotropic representation distortion to preserve output behavior more effectively than existing methods.
-
GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization
GoQuant formulates quantization as dual-basis geometric projection to create higher-resolution residual lattices for 3-bit PoT transformer quantization using only shift-and-add, reporting 6.10 perplexity on LLaMA-2-7B.
- SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models