Changyao Tian

Changyao's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers about 5 hours ago

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Paper • 2603.12264 • Published about 20 hours ago • 13

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

Paper • 2603.12247 • Published about 20 hours ago • 20

upvoted a paper 1 day ago

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Paper • 2603.09877 • Published 3 days ago • 39

authored a paper 2 days ago

InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Paper • 2603.09877 • Published 3 days ago • 39

updated a model 2 days ago

InternVL-U/InternVL-U

Updated 2 days ago • 79 • 17

upvoted 2 papers 5 months ago

InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

Paper • 2510.11341 • Published Oct 13, 2025 • 35

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Paper • 2510.11027 • Published Oct 13, 2025 • 23

updated 2 models 5 months ago

OpenGVLab/NaViL-9B

16B • Updated Oct 10, 2025 • 4 • 1

OpenGVLab/NaViL-2B

4B • Updated Oct 10, 2025 • 7 • 1

updated a collection 5 months ago

NaViL

Collection

[NeurIPS 2025] Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints • 3 items • Updated 11 days ago • 3

published a model 5 months ago

OpenGVLab/NaViL-9B

16B • Updated Oct 10, 2025 • 4 • 1

updated a collection 5 months ago

NaViL

Collection

[NeurIPS 2025] Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints • 3 items • Updated 11 days ago • 3

published a model 5 months ago

OpenGVLab/NaViL-2B

4B • Updated Oct 10, 2025 • 7 • 1

authored 5 papers 5 months ago

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Paper • 2406.08418 • Published Jun 12, 2024 • 32

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 214

GenExam: A Multidisciplinary Text-to-Image Exam

Paper • 2509.14232 • Published Sep 17, 2025 • 21

Sequential Diffusion Language Models

Paper • 2509.24007 • Published Sep 28, 2025 • 46

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Paper • 2510.08565 • Published Oct 9, 2025 • 21

upvoted a paper 5 months ago

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

Paper • 2510.08565 • Published Oct 9, 2025 • 21

upvoted a collection 5 months ago

NaViL

Collection

[NeurIPS 2025] Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints • 3 items • Updated 11 days ago • 3