Haiwen Diao's picture

Haiwen Diao

Paranioar

·

https://Paranioar.github.io/

AI & ML interests

Vision-and-Language, Parameter-efficient Transfer Learning, Multi-modal Large Language Model

Recent Activity

updated a dataset about 3 hours ago

Paranioar/datacomp

updated a dataset about 5 hours ago

Paranioar/datacomp

updated a dataset about 7 hours ago

Paranioar/datacomp

View all activity

Organizations

commented a paper 16 days ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published 16 days ago • 62 •

commented a paper 3 months ago

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Paper • 2510.14979 • Published Oct 16, 2025 • 66 •

commented a paper 11 months ago

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

Paper • 2502.06788 • Published Feb 10, 2025 • 13 •

commented 2 papers over 1 year ago

SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning

Paper • 2407.07523 • Published Jul 10, 2024 • 6 •

Unveiling Encoder-Free Vision-Language Models

Paper • 2406.11832 • Published Jun 17, 2024 • 54 •