ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Minjia Zhang

Minjia Zhang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

10

papers

1,262

total citations

papers (10)

ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers

NEURIPS 2022arXiv

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping

NEURIPS 2020arXiv

The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models

NEURIPS 2022arXiv

DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing

NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM

NEURIPS 2021arXiv

InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

XTC: Extreme Compression for Pre-trained Transformers Made Simple and Efficient

AdaTune: Adaptive Tensor Program Compilation Made Efficient