Lulu Hu
4 papers · 2023–2026 · 4 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
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
post-training quantization
(1)
vision transformer
(1)
object detection
(1)
convolutional neural network
(1)
multimodal large language model
(1)
data synthesis
(1)
activation sparsity
(1)
top-k selection
(1)
instruction generation
(1)
large language model
(1)
reasoning structure
(1)
cross-modal compensation
(1)
dual-processing system
(1)
hierarchical dag
(1)
modality-aware smoothing
(1)
svd whitening
(1)
sparsification
(1)
layerwise orthogonal rotations
(1)
perplexity gap
(1)
wall-clock time speed-up
(1)
Papers
MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models
CVPR 2026
Enhanced Data Synthesis for LLM through Reasoning Structures Generated by Hierarchical GFlowNet
ACL 2025
La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
ICML 2025
A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism
ICCV 2023