影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
70.64/100
前 2.5%
全站排名 #1,622
发表论文14 篇
平均评分
年均产出4.7 篇/年
Amir Yazdanbakhsh
研究方向
Efficient Large Language Models · Machine Learning for Code · Machine Learning for System · Computer Architecture · Systems · High-Level Synthesis · Approximate Computing
45
SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
ICLR 2026Rejected
三作15
QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
ICLR 2026Rejected
24
OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction
ICLR 2026Rejected
通讯6
MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference
ICLR 2026Rejected
通讯26
Effective Interplay between Sparsity and Quantization: From Theory to Practice
ICLR 2025Spotlight
通讯23
The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
ICLR 2025Poster
10
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
ICML 2025Poster
25
SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
ICLR 2025Poster
二作15
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
ICML 2025Poster
11
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
ICML 2025Poster
二作