Yuki Asano

yukimasano's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored 17 papers about 1 month ago

Self-Ordering Point Clouds

Paper • 2304.00961 • Published Apr 3, 2023

Small Visual Language Models can also be Open-Ended Few-Shot Learners

Paper • 2310.00500 • Published Sep 30, 2023

A critical analysis of self-supervision, or what we can learn from a single image

Paper • 1904.13132 • Published Apr 30, 2019

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

Paper • 2310.08584 • Published Oct 12, 2023 • 2

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models

Paper • 2102.04130 • Published Feb 8, 2021

VaLID: Variable-Length Input Diffusion for Novel View Synthesis

Paper • 2312.08892 • Published Dec 14, 2023

The LLM Surgeon

Paper • 2312.17244 • Published Dec 28, 2023 • 9

Object-Centric Diffusion for Efficient Video Editing

Paper • 2401.05735 • Published Jan 11 • 7

PASS: An ImageNet replacement for self-supervised pretraining without humans

Paper • 2109.13228 • Published Sep 27, 2021

PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs

Paper • 2402.08657 • Published Feb 13 • 1

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

Paper • 2308.11796 • Published Aug 22, 2023 • 1

Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding

Paper • 2402.16844 • Published Feb 26

Self-Guided Diffusion Models

Paper • 2210.06462 • Published Oct 12, 2022 • 2

Bitune: Bidirectional Instruction-Tuning

Paper • 2405.14862 • Published May 23 • 1

SIGMA: Sinkhorn-Guided Masked Video Modeling

Paper • 2407.15447 • Published Jul 22 • 7

NeCo: Improving DINOv2's spatial representations in 19 GPU hours with Patch Neighbor Consistency

Paper • 2408.11054 • Published Aug 20 • 11

TVBench: Redesigning Video-Language Evaluation

Paper • 2410.07752 • Published Oct 10 • 5

upvoted a paper about 1 month ago

TVBench: Redesigning Video-Language Evaluation

Paper • 2410.07752 • Published Oct 10 • 5

liked a dataset about 1 month ago

FunAILab/TVBench

Viewer • Updated 13 days ago • 2.53k • 793 • 10

upvoted a paper 3 months ago

NeCo: Improving DINOv2's spatial representations in 19 GPU hours with Patch Neighbor Consistency

Paper • 2408.11054 • Published Aug 20 • 11