0

Fangyun Wei

Papers
19

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
19papers

Authored papers

19

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

arXiv 2026

2026

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

arXiv 2026

2026

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

arXiv 2025

2025

Spatia: Video Generation with Updatable Spatial Memory

arXiv 2025

2025

Animate Any Character in Any World

arXiv 2025

2025

A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars

arXiv 2024

2024

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

arXiv 2024

2024

Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

arXiv 2024

2024

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

CVPR 2024 1

2024

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models

arXiv 2024

2024

Two-shot Video Object Segmentation

CVPR 2023 1

2023

Side Adapter Network for Open-Vocabulary Semantic Segmentation

CVPR 2023 1

2023

Attentive Mask CLIP

ICCV 2023 1

2022

Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model

CVPR 2022 1

2022

Unsupervised Prompt Learning for Vision-Language Models

arXiv 2022

2022

Aligning Pretraining for Detection via Object-Level Contrastive Learning

NeurIPS 2021 12

2021

End-to-End Semi-Supervised Object Detection with Soft Teacher

ICCV 2021 10

2021

Global Context Networks

arXiv 2020

2020

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

NeurIPS 2020 12

2020

Affiliations

No known affiliations.

Frequent co-authors

10

from 19 papers