Selected Publications

NVFP4 pre-training with MS-EDEN, an unbiased gradient estimator that reduces quantization error, and GPU kernels for NVIDIA Blackwell.

A study of MXFP4 and NVFP4 inference, introducing Micro-Rotated-GPTQ and GPU kernels tailored to the constraints of microscaling formats.

An open multilingual language model effort with transparent training recipes and a focus on data compliance and language coverage.

End-to-end FP4 training of language models, combining low-precision scaling laws with CUDA kernels for Blackwell GPUs.

Quantization-aware training with Hadamard normalization and a trust gradient estimator, enabling stable training down to 1-bit weights and activations.

A theoretical link between layer reconstruction error and model perplexity, leading to data-free quantization and non-uniform bit allocation.

AQLM compresses language model weights through additive quantization, targeting accurate inference at very low bit widths.