Umberto Michieli
15 papers · 2020–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (11) 🌍 Conference Polyglot (7) 🏃 Academic Marathon (5) 🌈 Renaissance Researcher (6)
🌍
Conference Polyglot
(7)
🏃
Academic Marathon
(5)
🐝
Cross-Pollinator
(11)
💎
Century Club
(14)
🗃️
Keyword Collector
(67)
⚡
Prolific Year
(5)
Conferences
EMNLP (4)
CVPR (2)
ICCV (2)
INTERSPEECH (2)
WACV (2)
AAAI (1)
ACL (1)
ECCV (1)
Top co-authors
Research topics
Keywords
large language model
(5)
model merging
(5)
continual learning
(5)
semantic segmentation
(4)
model compression
(4)
on-device deployment
(3)
multi-task learning
(3)
low-rank adapter
(3)
parameter-efficient fine-tuning
(2)
on-device inference
(2)
catastrophic forgetting
(2)
low-rank adaptation
(2)
model personalization
(2)
compositional multi-tasking
(2)
text summarization
(1)
source-free domain adaptation
(1)
speech recognition
(1)
text-to-image synthesis
(1)
image generation
(1)
natural language processing
(1)
Papers
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
ACL 2026
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
CVPR 2025
On-device System of Compositional Multi-tasking in Large Language Models
EMNLP 2025
HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging
EMNLP 2025
Efficient Compositional Multi-tasking for On-device Large Language Models
EMNLP 2025
LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
ICCV 2025
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
EMNLP 2024
HOP to the Next Tasks and Domains for Continual Learning in NLP
AAAI 2024
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
WACV 2023
Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics
INTERSPEECH 2023
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization
INTERSPEECH 2023
Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings
WACV 2021
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
CVPR 2021
RECALL: Replay-Based Continual Learning in Semantic Segmentation
ICCV 2021
GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild
ECCV 2020