5 17 10

Yuhao Dong

THUdyh

AI & ML interests

None yet

Recent Activity

liked a model about 16 hours ago

THUdyh/Insight-V-Reason

posted an update 3 days ago

🚀🚀🚀Introducing Insight-V! An early attempt towards o1-like multi-modal reasoning. We offer a structured long-chain visual reasoning data generation pipeline and a multi-agent system to unleash the reasoning potential of MLLMs. 📜 Paper: https://arxiv.org/abs/2411.14432 🛠️ Github: https://github.com/dongyh20/Insight-V 💼 Model Weight: https://huggingface.co/collections/THUdyh/insight-v-673f5e1dd8ab5f2d8d332035

authored a paper 3 days ago

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

View all activity

Organizations

THUdyh's activity

upvoted a collection 3 days ago

Insight-V

Collection

Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models • 5 items • Updated 3 days ago • 7

upvoted a paper 3 days ago

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

Paper • 2411.14432 • Published 3 days ago • 16

upvoted a paper 20 days ago

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Paper • 2411.02265 • Published 20 days ago • 24

upvoted a paper about 1 month ago

Aria: An Open Multimodal Native Mixture-of-Experts Model

Paper • 2410.05993 • Published Oct 8 • 107

upvoted 3 papers about 2 months ago

Video Instruction Tuning With Synthetic Data

Paper • 2410.02713 • Published Oct 3 • 37

MIO: A Foundation Model on Multimodal Tokens

Paper • 2409.17692 • Published Sep 26 • 50

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published Sep 25 • 103

upvoted a collection 2 months ago

Oryx

Collection

Oryx: One Multi-Modal LLM for On-Demand Spatial-Temporal Understanding • 5 items • Updated Oct 23 • 15

upvoted 3 papers 2 months ago

Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

Paper • 2409.12961 • Published Sep 19 • 24

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

Paper • 2409.12957 • Published Sep 19 • 18

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Paper • 2409.12191 • Published Sep 18 • 75

upvoted 5 papers 4 months ago

Achieving Human Level Competitive Robot Table Tennis

Paper • 2408.03906 • Published Aug 7 • 26

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks

Paper • 2408.03615 • Published Aug 7 • 30

LLaVA-OneVision: Easy Visual Task Transfer

Paper • 2408.03326 • Published Aug 6 • 59

Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model

Paper • 2408.00754 • Published Aug 1 • 21

Efficient Inference of Vision Instruction-Following Models with Elastic Cache

Paper • 2407.18121 • Published Jul 25 • 16

upvoted a paper about 1 year ago

Octopus: Embodied Vision-Language Programmer from Environmental Feedback

Paper • 2310.08588 • Published Oct 12, 2023 • 34