Dan Alistarh
- Papers
- 36
Cite
Notes
Only stored in your browser.
Authored papers
36Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
arXiv 2026
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
arXiv 2026
MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
arXiv 2026
DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
arXiv 2026
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
arXiv 2025
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
arXiv 2025
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
arXiv 2025
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
arXiv 2025
Efficient Data Selection at Scale via Influence Distillation
arXiv 2025
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
arXiv 2025
DarwinLM: Evolutionary Structured Pruning of Large Language Models
arXiv 2025
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
arXiv 2025
MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models
arXiv 2024
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
arXiv 2024
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
arXiv 2024
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
arXiv 2024
Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning
arXiv 2024
Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant
arXiv 2024
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search
arXiv 2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
arXiv 2024
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
arXiv 2024
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
arXiv 2023
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
arXiv 2023
QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models
arXiv 2023
Sparse Fine-tuning for Inference Acceleration of Large Language Models
arXiv 2023
ZipLM: Inference-Aware Structured Pruning of Language Models
ziplm-inference-aware-structured-pruning-of
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
arXiv 2023
SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks
arXiv 2023
Error Feedback Can Accurately Compress Preconditioners
arXiv 2023
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
arXiv 2022
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models
arXiv 2022
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
arXiv 2022
L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning
arXiv 2022
CrAM: A Compression-Aware Minimizer
arXiv 2022
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
NeurIPS 2021 12
Model compression via distillation and quantization
model-compression-via-distillation-and-1
Affiliations
Frequent co-authors
10from 36 papers