publications

Papers.

Most recent list at Google scholar. * denote equal contribution, ⁺ denotes equal contribution with random order.

2024

  1. bitune.png
    Bitune: Bidirectional Instruction-Tuning
    Dawid Kopiczko, Tijmen Blankevoort, and Yuki M. Asano
    arXiv:2405.14862, 2024
  2. llm2slm.png
    Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
    Benjamin Bergner, Andrii Skliar, Amelie Royer, Tijmen Blankevoort, Yuki M Asano, and Babak Ehteshami Bejnordi
    arXiv:2402.16844, 2024
  3. pin.png
    PIN: Positional Insert unlocks object localisation abilities in VLMs
    Michael Dorkenwald, Nimrod Barazani, Cees G. M. Snoek, and Yuki M Asano
    CVPR, 2024
  4. UnCo.png
    Learning to Count without Annotations
    Lukas Knobel, Tengda Han*, and Yuki M. Asano*
    CVPR, 2024
  5. text_flow.png
    Flow Matching for Conditional Text Generation in a Few Sampling Steps
    Vincent Tao Hu, Di Wu, Yuki M Asano, Pascal Mettes, Basura Fernando, Bjorn Ommer, and Cees G. M. Snoek
    EACL, 2024
  6. protect.jpg
    Protect Your Score: Contact-tracing With Differential Privacy Guarantees
    Rob Romijnders, Yuki M Asano, Christos Louizos, and Max Welling
    AAAI, 2024
  7. vera.png
    VeRA: Vector-based Random Matrix Adaptation
    Dawid Kopiczko, Tijmen Blankevoort, and Yuki M. Asano
    ICLR, 2024
  8. llmsurgeon.png
    The LLM Surgeon
    Tycho FA Ouderaa, Markus Nagel, Mart Baalen, Yuki M Asano, and Tijmen Blankevoort
    ICLR, 2024
  9. dora.png
    Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
    Shashanka Venkataramanan, Mamshad Nayeem Rizve, João Carreira, Yuki M. Asano⁺, and Yannis Avrithis⁺
    ICLR, 2024
  10. skipat.png
    Skip-Attention: Improving Vision Transformers by Paying Less Attention
    Shashanka Venkataramanan, Amir Ghodrati, Yuki M Asano, Fatih Porikli, and Amirhossein Habibian
    ICLR, 2024

2023

  1. motion.png
    Motion Flow Matching for Human Motion Synthesis and Editing
    Vincent Tao Hu, Wenzhe Yin, Pingchuan Ma, Yunlu Chen, Basura Fernando, Yuki M Asano, Efstratios Gavves, Pascal Mettes, Bjorn Ommer, and Cees G. M. Snoek
    arXiv: 2312.08895, 2023
  2. selfvocab.png
    Self-Guided Open-Vocabulary Semantic Segmentation
    Osman Ülger, Maksymilian Kulicki, Yuki M. Asano, and Martin R. Oswald
    arXiv: 2312.04539, 2023
  3. selfguide.png
    Guided Diffusion from Self-Supervised Diffusion Features
    Vincent Tao Hu, Yunlu Chen, Mathilde Caron, Yuki M. Asano, Cees G. M. Snoek, and Bjorn Ommer
    arXiv: 2312.08825, 2023
  4. valid.png
    VaLID: Variable-Length Input Diffusion for Novel View Synthesis
    Shijie Li, Farhad G. Zanjani, Haitam Ben Yahia, Yuki M. Asano, Jürgen Gall, and Amirhossein Habibian
    arXiv: 2312.08892, 2023
  5. deltamask.png
    Federated Fine-Tuning of Foundation Models via Probabilistic Masking
    Vasileios Tsouvalas, Yuki M. Asano, and Aaqib Saeed
    arXiv: 2311.17299, 2023
  6. secat.png
    Small Visual Language Models can also be Open-Ended Few-Shot Learners
    Mohammad Mahdi Derakhshani⁺, Ivona Najdenkoska⁺, Marcel Worring*, Cees G.M. Snoek*, and Yuki M. Asano*
    arXiv: 2310.00500, 2023
  7. effpde.png
    Efficient Neural PDE-Solvers using Quantization Aware Training
    Winfried Dool, Tijmen Blankevoort, Max Welling, and Yuki M. Asano
    ICCV Workshop on Resource Efficient Deep Learning for Computer Vision, 2023
  8. timetuning.png
    Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations
    Mohammadreza Salehi, Efstratios Gavves, Cees G. M. Snoek, and Yuki M. Asano
    ICCV, 2023
  9. self_points.png
    Self-Ordering Point Clouds
    Pengwan Yang, Cees G. M. Snoek*, and Yuki M. Asano*
    ICCV, 2023
  10. biscuit.png
    BISCUIT: Causal Representation Learning from Binary Interactions
    Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, and Efstratios Gavves
    UAI, 2023
  11. survey.png
    Towards Label-Efficient Incremental Learning: A Survey
    Mert Kilickaya, Joost Weijer, and Yuki M. Asano
    arXiv: 2302.00353, 2023
  12. sgd.png
    Self-Guided Diffusion Models
    Vincent Tao Hu, David W. Zhang, Yuki M. Asano, Gertjan J. Burghouts, and Cees G.M. Snoek
    CVPR, 2023
  13. notime.png
    No time to waste: practical statistical contact tracing with few low-bit messages
    Rob Romijnders, Yuki M Asano, Christos Louizos, and Max Welling
    AISTATS, 2023
  14. kd.png
    The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
    Yuki M. Asano*, and Aaqib Saeed*
    ICLR, 2023
  15. instant.png
    Causal Representation Learning for Instantaneous and Temporal Effects
    Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, and Efstratios Gavves
    ICLR, 2023

2022

  1. prompt.png
    Prompt Generation Networks for Efficient Adaptation of Frozen Vision Transformers
    Jochem Loedeman, Maarten Stol, Tengda Han, and Yuki M. Asano
    arxiv preprint arxiv:2210.06466, 2022
  2. leopart.png
    Self-supervised learning of object parts for semantic segmentation
    Adrian Ziegler, and Yuki M Asano
    CVPR, 2022
  3. gpt3.png
    Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements
    Conrad Borchers, Dalia Sara Gala, Benjamin Gilburt, Eduard Oravkin, Wilfried Bounsi, Yuki M. Asano, and Hannah Rose Kirk
    NAACL workshop on Gender Bias in NLP, 2022
  4. reverse_probing.png
    Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing
    Iro Laina, Yuki M. Asano, and Andrea Vedaldi
    ICLR, 2022
  5. citris.png
    CITRIS: Causal Identifiability from Temporal Intervened Sequences
    Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, and Efstratios Gavves
    ICML, 2022
  6. vtc.png
    VTC: Improving Video-Text Retrieval with User Comments
    Laura Hanu, Yuki M Asano, Thewlis James, and Christian Rupprecht
    ECCV, 2022
  7. less.jpeg
    Less Than Few: Self-shot Video Instance Segmentation
    Pengwan Yang, Yuki M Asano, Pascal Mettes, and Cees G.M. Snoek
    ECCV, 2022
  8. avdet.png
    Self-supervised object detection from audio-visual correspondence
    Triantafyllos Afouras*, Yuki M. Asano*, Francois Fagan, Andrea Vedaldi, and Florian Metze
    CVPR, 2022

2021

  1. ramsey.png
    Emergent inequality and business cycles in a simple behavioral macroeconomic model
    Yuki M. Asano, Jakob J. Kolb, Jobst Heitzig, and J. Doyne Farmer
    Proceedings of the National Academy of Sciences (PNAS), 2021
  2. motionformer.png
    Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
    Mandela Patrick*, Dylan Campbell*, Yuki M. Asano*, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, and João F. Henriques
    NeurIPS, 2021
  3. memes.png
    Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset
    Hannah Kirk, Yennie Jun, Paulius Rauba, Gal Wachtel, Ruining Li, Xingjian Bai, Noah Broestl, Martin Doff-Sotta, Aleksandar Shtedritski, and Yuki M Asano
    ACL WOAH workshop 2021, 2021
  4. support_set.png
    Support-set bottlenecks for video-text representation learning
    Mandela Patrick*, Po-Yao Huang*, Yuki M. Asano*, Florian Metze, Alexander Hauptmann, João F. Henriques, and Andrea Vedaldi
    ICLR, 2021
  5. gdt.png
    On Compositions of Transformations in Contrastive Self-Supervised Learning
    Mandela Patrick*, Yuki M. Asano*, Polina Kuznetsova, Ruth Fong, João F. Henriques, Geoffrey Zweig, and Andrea Vedaldi
    ICCV, 2021
  6. gpt-2.png
    Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models
    Hannah Kirk, Yennie Jun, Haider Iqbal, Elias Benussi, Filippo Volpin, Frederic A. Dreyer, Aleksandar Shtedritski, and Yuki M. Asano
    NeurIPS, 2021
  7. privacy.png
    Privacy-preserving Object Detection
    Peiyang He, Charlie Griffin, Krzysztof Kacprzyk, Artjom Joosen, Michael Collyer, Aleksandar Shtedritski, and Yuki M. Asano
    arXiv, 2021
  8. stica.png
    Space-time crop & attend: Improving cross-modal video representation learning
    Mandela Patrick*, Po-Yao Huang*, Yuki M. Asano*, Ishan Misra, Florian Metze, Andrea Vedaldi, and João F. Henriques
    ICCV, 2021
  9. pass.png
    PASS: An ImageNet replacement for self-supervised pretraining without humans
    Yuki M. Asano, Christian Rupprecht, Andrew Zisserman, and Andrea Vedaldi
    NeurIPS Track on Datasets and Benchmarks, 2021

2020

  1. labelling_videos.gif
    Labelling unlabelled videos from scratch with multi-modal self-supervision
    Yuki M. Asano, Mandela Patrick, Christian Rupprecht, and Andrea Vedaldi
    NeurIPS, 2020
  2. self-clusters.jpg
    Self-labelling via simultaneous clustering and representation learning
    Yuki M. Asano, Christian Rupprecht, and Andrea Vedaldi
    ICLR, 2020
  3. ameyoko_crop.jpg
    A critical analysis of self-supervision, or what we can learn from a single image
    Yuki M. Asano, Christian Rupprecht, and Andrea Vedaldi
    ICLR, 2020