PPaperPicks

Umberto Michieli

13 papers at tracked venues · 6 at CORE A* · active 2024–2026

Venues

Frequent coauthors

Mete Ozay
×11
Jijoong Moon
×6
Ondrej Bohdal
×5
Pietro Zanuttigh
×3
Kyeng-Hun Lee
×3
Hyeonmok Ko
×3
Donald Shenaj
×2
Taha Ceritli
×2
Jialin Zhao
×2
Yingtao Zhang
×2
Carlo Vittorio Cannistraci
×2
Alessandro Muscoloni
×1

Papers

  1. K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
    ACL 2026 ·
    Donald Shenaj
    ,
    Ondrej Bohdal
    ,
    Taha Ceritli
    ,
    Mete Ozay
    ,
    Pietro Zanuttigh
    , Umberto Michieli
  2. Adaptive Cannistraci-Hebb Network Automata Modelling of Complex Networks for Path-based Link Prediction
    NeurIPS 2025 ·
    Jialin Zhao
    ,
    Alessandro Muscoloni
    , Umberto Michieli,
    Yingtao Zhang
    ,
    Carlo Vittorio Cannistraci
  3. Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
    NeurIPS 2025 ·
    Yingtao Zhang
    ,
    Diego Cerretti
    ,
    Jialin Zhao
    ,
    Wenjing Wu
    ,
    Ziheng Liao
    , Umberto Michieli,
    Carlo Vittorio Cannistraci
  4. DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
    CVPR 2025 ·
    Emanuele Aiello
    , Umberto Michieli,
    Diego Valsesia
    ,
    Mete Ozay
    ,
    Enrico Magli
  5. Efficient Compositional Multi-tasking for On-device Large Language Models
    EMNLP 2025 ·
    Ondrej Bohdal
    ,
    Mete Ozay
    ,
    Jijoong Moon
    ,
    Kyeng-Hun Lee
    ,
    Hyeonmok Ko
    , Umberto Michieli
  6. HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging
    EMNLP 2025 ·
    Taha Ceritli
    ,
    Ondrej Bohdal
    ,
    Mete Ozay
    ,
    Jijoong Moon
    ,
    Kyeng-Hun Lee
    ,
    Hyeonmok Ko
    , Umberto Michieli
  7. LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
    ICCV 2025 ·
    Donald Shenaj
    ,
    Ondrej Bohdal
    ,
    Mete Ozay
    ,
    Pietro Zanuttigh
    , Umberto Michieli
  8. On-device System of Compositional Multi-tasking in Large Language Models
    EMNLP 2025 ·
    Ondrej Bohdal
    ,
    Konstantinos Theodosiadis
    ,
    Asterios Mpatziakas
    ,
    Dimitrios Filippidis
    ,
    Iro Spyrou
    ,
    Christos Zonios
    ,
    Anastasios Drosou
    ,
    Dimosthenis Ioannidis
    ,
    Kyeng-Hun Lee
    ,
    Jijoong Moon
    ,
    Hyeonmok Ko
    ,
    Mete Ozay
    , Umberto Michieli
  9. Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection
    IROS 2024 ·
    Francesco Barbato
    , Umberto Michieli,
    Jijoong Moon
    ,
    Pietro Zanuttigh
    ,
    Mete Ozay
  10. Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics
    IROS 2024 ·
    Elena Camuffo
    , Umberto Michieli,
    Simone Milani
    ,
    Jijoong Moon
    ,
    Mete Ozay
  11. HOP to the Next Tasks and Domains for Continual Learning in NLP
    AAAI 2024 · Umberto Michieli,
    Mete Ozay
  12. Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
    EMNLP 2024 ·
    Hasan Hammoud
    , Umberto Michieli,
    Fabio Pizzati
    ,
    Philip Torr
    ,
    Adel Bibi
    ,
    Bernard Ghanem
    ,
    Mete Ozay
  13. Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search
    IROS 2024 ·
    Kirill Paramonov
    ,
    Jia-Xing Zhong
    , Umberto Michieli,
    Jijoong Moon
    ,
    Mete Ozay