0

Yun Fu

Papers
22

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
22papers

Authored papers

22

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

arXiv 2026

2026

Demystifying When Pruning Works via Representation Hierarchies

arXiv 2026

2026

Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks

arXiv 2026

2026

Trajectory Prediction Meets Large Language Models: A Survey

arXiv 2025

2025

Boosting Large Language Models with Mask Fine-Tuning

arXiv 2025

2025

Token Dynamics: Towards Efficient and Dynamic Video Token Representation for Video Large Language Models

arXiv 2025

2025

Cautious Next Token Prediction

arXiv 2025

2025

Efficient Modulation for Vision Networks

arXiv 2024

2024

OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising

CVPR 2024 1

2024

Image as Set of Points

arXiv 2023

2023

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

unicontrol-a-unified-diffusion-model-for

2023

Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution

ICCV 2023 1

2023

Frame Flexible Network

CVPR 2023 1

2023

Making Reconstruction-based Method Great Again for Video Anomaly Detection

arXiv 2023

2023

Explainable Anomaly Detection in Images and Videos: A Survey

arXiv 2023

2023

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

arXiv 2022

2022

Real-Time Neural Light Field on Mobile Devices

CVPR 2023 1

2022

Rethinking Adam: A Twofold Exponential Moving Average Approach

adapting-stepsizes-by-momentumized-gradients-1

2021

Self-Directed Online Machine Learning for Topology Optimization

arXiv 2020

2020

What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective

arXiv 2020

2020

Arc-support Line Segments Revisited: An Efficient and High-quality Ellipse Detection

arXiv 2018

2018

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

image-super-resolution-using-very-deep-1

2018

Affiliations

No known affiliations.

Frequent co-authors

10

from 22 papers