Challenge: Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs.
Approach: They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm .
Outcome: The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16.

Similar Papers

PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models (2026.acl-srw)

Copied to clipboard

Challenge: Quantization Aware Training (QAT) is expensive to train and unscalable to large models.
Approach: They propose a parameter-efficient framework targeting per-channel 4-bit weight-activation quantization of large language models.
Outcome: The proposed framework preserves accuracy within 0.11 percentage points of the full-precision baseline on Llama-2-7B zero-shot tasks while training only 1.26% of total parameters.
Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for dynamic quantization are hardware-unfriendly and often lead to large quantization errors in static scenarios.
Approach: They propose a Static Hierarchical Mix-precision Quantization method which quantifies both inter-layer and intra-layer sensitivity through unified derivations involving Hessian.
Outcome: The proposed method achieves 75.58% on zero-shot reasoning tasks while yielding average speedup of 2.86.
Achieving binary weight and activation for LLMs using Post-Training Quantization (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for quantizing large language models suffer from performance degradation when weights are quantized to 1 bit.
Approach: They propose a post-training quantization framework with W(1+1)A(14) configuration . they propose utilizing Hessian-aware fine-grained grouping along with an EM-based quantization scheme .
Outcome: The proposed method surpasses state-of-the-art (SOTA) LLM quantization baselines on W2A4 across multiple tasks.
BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs (2026.acl-long)

Copied to clipboard

Challenge: Large language models have driven major progress in NLP, but memory and compute requirements hinder practical deployment.
Approach: They propose a framework that preserves high accuracy while achieving 1-bit weight quantization . the orthogonal-kronecker transformation learns an orthogonale mapping via EM minimization - a new approach to quantization is proposed .
Outcome: The proposed framework achieves 1-bit weight quantization with low activations with low-bit activations.
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Quantization is a practical solution for deploying Large Language Models in resource-constrained environments.
Approach: They propose an outlier-safe pre-training approach that prevents outlier formation . they validate a 1.4B-parameter model on 1 trillion tokens with no outliers .
Outcome: The proposed model achieves a 35.7 average score on 1 trillion tokens with 2% training overhead.
pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for building efficient large language models with sub 2-bit weights are lacking in accuracy and scalability.
Approach: They propose a method that decouples parameters by splitting linear layers into two specialized branches.
Outcome: The proposed method achieves state-of-the-art performance in extremely low-bit quantization.
CoopQ: Cooperative Game Inspired Layerwise Mixed Precision Quantization for LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for large language models struggle when the average precision drops below four bits, limiting deployment on resourceconstrained devices such as mobiles, edge sensors, or standard GPUs.
Approach: They propose a game-like game-inspired mixed-precision quantization method which translates these Shapley estimates into a binary quadratic optimization formulation, assigning either 2 or 4-bit precision to layers under strict memory constraints.
Outcome: The proposed method reduces Perplexity by 20 – 80 % across average precisions spanning 4 bit down to 2 bit, compared to methods relying on isolated metrics.
PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for sub 2-bit quantization introduce an extra 1-bit or more per weight.
Approach: They propose a sub 2-bit post-training quantization method that enables weight quantization to 1.61-bit for the first time.
Outcome: The proposed method reduces the upper bound of quantization error to 1.61-bit for the first time.
DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models (2024.emnlp-industry)

Copied to clipboard

Challenge: Quantization-aware Training (QAT) is a popular technique for reducing memory usage and improving computational efficiency in large language models.
Approach: They propose a weight-decomposed low-rank quantization-aware training approach that integrates QAT with a group-specific quantization magnitude adjustment.
Outcome: The proposed method outperforms the state-of-the-art method on LLaMA and LLama2 models.
EfficientQAT: Efficient Quantization-Aware Training for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Quantization-aware training (QAT) is a low-bit training solution that requires substantial training resources.
Approach: They propose an algorithm that reduces memory consumption by low-bit representations with minimal accuracy loss.
Outcome: EfficientQAT achieves 2-bit Llama-2-70B model on single GPU in 41 hours . compared to previous methods, it obtains model with less than 3 points accuracy degradation .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations