GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 1 day ago • 4
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 1 day ago • 4
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 1 day ago • 4
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling Paper • 2604.18556 • Published Apr 20 • 7
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling Paper • 2604.18556 • Published Apr 20 • 7
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning Paper • 2605.07850 • Published 13 days ago • 18