Yi-Hao's picture

42 26

Yi-Hao

yihaopeng

·

https://www.yihaopeng.tw/

AI & ML interests

None yet

Recent Activity

updated a collection 5 minutes ago

updated a collection about 5 hours ago

updated a collection about 7 hours ago

View all activity

Organizations

upvoted an article 15 days ago

Article

Introducing NVIDIA Cosmos Policy for Advanced Robot Control

15 days ago

•

38

upvoted a collection 30 days ago

Gemma 3 Release

28 items • Updated Aug 11, 2025 • 610

upvoted 2 collections about 1 month ago

Cosmos-Reason2

Cosmos Reason 2 is an open, customizable, reasoning vision language model (VLM) for physical AI and robotics • 16 items • Updated 9 days ago • 21

Qwen3-VL-Embedding

2 items • Updated Jan 8 • 58

upvoted 2 collections about 2 months ago

T5Gemma 2

3 items • Updated Dec 18, 2025 • 66

Molmo2

Artifacts for the Molmo2 release • 6 items • Updated Dec 23, 2025 • 35

upvoted a collection 3 months ago

FLUX.2

Our second generation of FLUX • 17 items • Updated 26 days ago • 125

upvoted 2 collections 5 months ago

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 182

Qwen3-VL

37 items • Updated Dec 31, 2025 • 624

upvoted 3 collections 6 months ago

FastVLM

Efficient Vision Encoding for Vision Language Models • 9 items • Updated Sep 2, 2025 • 108

GLM-4.1V-Thinking

5 items • Updated Jul 2, 2025 • 57

InternVL3.5

This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated Sep 28, 2025 • 105

upvoted 2 collections 10 months ago

Perception LM

7 items • Updated Apr 17, 2025 • 63

Kimi-VL-A3B

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 7 items • Updated 18 days ago • 78

upvoted a paper 11 months ago

Modifying Large Language Model Post-Training for Diverse Creative Writing

Paper • 2503.17126 • Published Mar 21, 2025 • 36

upvoted 4 collections 11 months ago

MambaVision

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. • 13 items • Updated 9 days ago • 35

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated Mar 20, 2025 • 96

SigLIP2

36 items • Updated Jul 10, 2025 • 107

Ovis2

Our latest advancement in multi-modal large language models (MLLMs) • 15 items • Updated Mar 25, 2025 • 65

upvoted a collection about 1 year ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 11 items • Updated Dec 31, 2025 • 557