Yuhao Dong

THUdyh

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning

upvoted a paper 3 months ago

Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios

upvoted a paper 3 months ago

V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning

View all activity

Organizations

THUdyh 's models 17

THUdyh/Oryx-7B

Text Generation • 8B • Updated Jul 30, 2025 • 76 • 12

THUdyh/Insight-V-Reason-LLaMA3

Text Generation • 8B • Updated Jul 4, 2025 • 16 • 4

THUdyh/Insight-V-Summary-LLaMA3

Text Generation • 8B • Updated Jul 4, 2025 • 11 • 4

THUdyh/Ola-7b

Any-to-Any • 9B • Updated Jun 23, 2025 • 141 • 45

THUdyh/Ola_speech_encoders

Updated Jun 23, 2025 • 1

THUdyh/Ola-Image

8B • Updated Jun 23, 2025 • 17 • 3

THUdyh/Oryx-1.5-7B

Video-Text-to-Text • 8B • Updated Mar 1, 2025 • 32 • 8

THUdyh/Oryx-ViT

Image Feature Extraction • Updated Mar 1, 2025 • 8

THUdyh/Oryx-34B

Video-Text-to-Text • 35B • Updated Mar 1, 2025 • 20 • 3

THUdyh/Ola-Video

Video-Text-to-Text • 8B • Updated Feb 25, 2025 • 29 • 1

THUdyh/Oryx-1.5-32B-Image

Text Generation • 33B • Updated Jan 15, 2025 • 15 • 1

THUdyh/Oryx-1.5-Image

Text Generation • 8B • Updated Jan 15, 2025 • 19

THUdyh/Insight-V-Reason

Text Generation • 8B • Updated Nov 22, 2024 • 63 • 10

THUdyh/Insight-V-Summary

Text Generation • 8B • Updated Nov 22, 2024 • 16 • 9

THUdyh/Oryx-1.5-32B

Text Generation • 33B • Updated Oct 22, 2024 • 20 • 1

THUdyh/Oryx-34B-Image

Text Generation • 35B • Updated Sep 23, 2024 • 17 • 2

THUdyh/Oryx-7B-Image

Text Generation • 8B • Updated Sep 23, 2024 • 21 • 3