Haowei Li
4 papers · 2024–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
neural network optimization
(2)
model compression
(2)
distributed learning
(1)
safety alignment
(1)
communication efficiency
(1)
backdoor attack
(1)
adversarial attack
(1)
adversarial defense
(1)
communication overhead
(1)
quantization-aware training
(1)
weight oscillation
(1)
gradient sparsification
(1)
large language model
(1)
solution space exploration
(1)
low-bitwidth quantization
(1)
rounding operation
(1)
neuron-wise error
(1)
model quantization
(1)
Papers
Allowing Oscillation Quantization: Overcoming Solution Space Limitation in Low Bit-Width Quantization
ICCV 2025
Durable Quantization Conditioned Misalignment Attack on Large Language Models
ICLR 2025
JointSQ: Joint Sparsification-Quantization for Distributed Learning
CVPR 2024
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
CVPR 2024