PaperHub

Dan Alistarh

~Dan_Alistarh7

23
论文总数
11.5
年均投稿
6.3
平均评分
接收情况19/23
会议分布
ICLR
10
NeurIPS
9
ICML
4

发表论文 (23 篇)

202516 篇

6.4
5

Efficient Data Selection at Scale via Influence Distillation

NeurIPS 2025Poster
6.3
4

EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search

ICLR 2025Rejected
7.0
4

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

ICLR 2025Poster
6.5
4

Scalable Mechanistic Neural Networks

ICLR 2025Poster
6.6
4

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search

ICML 2025Poster
7.5
4

Wasserstein Distances, Neuronal Entanglement, and Sparsity

ICLR 2025Spotlight
4.8
3

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

ICML 2025Poster
5.5
4

Quantized Optimistic Dual Averaging with Adaptive Layer-wise Compression

ICLR 2025Rejected
6.7
3

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws

ICLR 2025Poster
4.9
4

Layer-wise Quantization for Quantized Optimistic Dual Averaging

ICML 2025Poster
7.5
5

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs

NeurIPS 2025Poster
7.3
4

Unified Scaling Laws for Compressed Representations

NeurIPS 2025Poster
4.0
4

UNAST: Unified framework for Neural Architecture Search for Transformers

ICLR 2025withdrawn
7.8
4

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

NeurIPS 2025Poster
6.1
4

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

ICML 2025Poster
7.8
5

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

NeurIPS 2025Spotlight
合作者 (20)