Zhongzhi Yu
8 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π Grand Slam
π
Trend Setter
ποΈ
Keyword Collector
(53)
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(5)
Deep Learning
(5)
Application Areas
(5)
Core AI Β· Artificial Intelligence
(4)
Learning Types Β· Deep Learning
(4)
Natural Language Processing
(2)
Speech & Audio
(2)
Architectures
(2)
Learning Types Β· Machine Learning
(2)
Recognition
(2)
Techniques
(2)
Computer Vision
(1)
Core AI Β· Computer Vision
(1)
Generation
(1)
Keywords
efficient computing
(2)
large language model
(2)
vision transformer
(2)
representation learning
(1)
feature learning
(1)
adversarial robustness
(1)
multi-task learning
(1)
self-supervised learning
(1)
knowledge transfer
(1)
knowledge distillation
(1)
data augmentation
(1)
speech recognition
(1)
speech processing
(1)
neural architecture search
(1)
multilingual speech processing
(1)
automatic speech recognition
(1)
few-shot learning
(1)
model pruning
(1)
adaptive computation
(1)
neural network pruning
(1)
Papers
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
ICML 2025
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
NeurIPS 2024
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
ICML 2024
Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning
CVPR 2023
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
ICML 2023
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
NeurIPS 2022
MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation
AAAI 2022
HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
ICLR 2021