Yuki M Asano
20 papers · 2021–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (23) π§ Keyword Pioneer π Conference Polyglot (9) π Cross-Pollinator (12) π Renaissance Researcher (6)
π
Interdisciplinary Bridge
β‘
Prolific Year
(8)
β
The Questioner
(2)
π₯
Unstoppable
(5)
π
Century Club
(20)
Conferences
ICLR (8)
ECCV (5)
ACL (1)
EMNLP (1)
ICCV (1)
ICML (1)
IJCNLP (1)
NAACL (1)
UAI (1)
Top co-authors
Keywords
optical character recognition
(2)
hateful meme detection
(2)
causal discovery
(2)
multimodal learning
(2)
text classification
(1)
image captioning
(1)
benchmark evaluation
(1)
self-supervised learning
(1)
transfer learning
(1)
attention mechanism
(1)
social media analysis
(1)
prompt engineering
(1)
optimal transport
(1)
bidirectional attention
(1)
embodied ai
(1)
temporal sequence
(1)
out-of-distribution generalization
(1)
instruction tuning
(1)
feature clustering
(1)
domain generalization
(1)
Papers
Near, far: Patch-ordering enhances vision foundation models' scene understanding
ICLR 2025
TULIP: Token-length Upgraded CLIP
ICLR 2025
Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
EMNLP 2025
MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning
ICCV 2025
SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery
ECCV 2024
Scaling Backwards: Minimal Synthetic Pre-training?
ECCV 2024
Rethinking Image Super Resolution from Training Data Perspectives
ECCV 2024
Skip-Attention: Improving Vision Transformers by Paying Less Attention
ICLR 2024
VeRA: Vector-based Random Matrix Adaptation
ICLR 2024
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
ICLR 2024
SIGMA: Sinkhorn-Guided Masked Video Modeling
ECCV 2024
Object-Centric Diffusion for Efficient Video Editing
ECCV 2024
BISCUIT: Causal Representation Learning from Binary Interactions
UAI 2023
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
ICLR 2023
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
ICLR 2023
Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing
ICLR 2022
CITRIS: Causal Identifiability from Temporal Intervened Sequences
ICML 2022
Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements
NAACL 2022
Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset
IJCNLP 2021
Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset
ACL 2021