Yiren Zhao
23 papers · 2019–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (6)
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(7)
🏃
Academic Marathon
(6)
🧬
Topic Evolution
🗃️
Keyword Collector
(94)
⚡
Prolific Year
(5)
💎
Century Club
(22)
🔥
Unstoppable
(7)
❓
The Questioner
(2)
Conferences
NIPS (6)
ICLR (4)
ICML (4)
ACL (3)
EMNLP (3)
CVPR (2)
ACML (1)
Top co-authors
Research topics
Keywords
model compression
(5)
large language model
(4)
federated learning
(2)
few-shot learning
(2)
adversarial attack
(2)
backdoor attack
(2)
memory optimization
(2)
memory efficiency
(2)
model quantization
(2)
adversarial machine learning
(2)
adversarial learning
(1)
training manipulation
(1)
transfer learning
(1)
human activity recognition
(1)
adversarial optimization
(1)
stochastic gradient descent
(1)
data poisoning
(1)
model architecture
(1)
neural network security
(1)
prompt engineering
(1)
Papers
Deep Kernel Fusion for Transformers
ACL 2026
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization
EMNLP 2025
QERA: an Analytical Framework for Quantization Error Reconstruction
ICLR 2025
Cached Multi-Lora Composition for Multi-Concept Image Generation
ICLR 2025
Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models
ACL 2025
Hardware and Software Platform Inference
ICML 2025
LQER: Low-Rank Quantization Error Reconstruction for LLMs
ICML 2024
GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
NIPS 2024
Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences
NIPS 2024
Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?
EMNLP 2023
MiliPoint: A Point Cloud Dataset for mmWave Radar
NIPS 2023
Revisiting Automated Prompting: Are We Actually Doing Better?
ACL 2023
Revisiting Structured Dropout
ACML 2023
Architectural Backdoors in Neural Networks
CVPR 2023
Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity
CVPR 2023
Dynamic Stashing Quantization for Efficient Transformer Training
EMNLP 2023
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
ICML 2022
Rapid Model Architecture Adaption for Meta-Learning
NIPS 2022
Markpainting: Adversarial Machine Learning meets Inpainting
ICML 2021
Manipulating SGD with Data Ordering Attacks
NIPS 2021
Pay Attention to Features, Transfer Learn Faster CNNs
ICLR 2020
Focused Quantization for Sparse CNNs
NIPS 2019
Dynamic Channel Pruning: Feature Boosting and Suppression
ICLR 2019