Guanyu Zhou

TheMartyr's activity

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

authored 4 papers about 3 hours ago

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Paper • 2410.04780 • Published Oct 7, 2024 • 1

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

Paper • 2509.00723 • Published Aug 31, 2025 • 1

CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation

Paper • 2510.06231 • Published Oct 1, 2025

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Paper • 2604.09531 • Published about 1 month ago • 8

upvoted a paper about 21 hours ago

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Paper • 2410.04780 • Published Oct 7, 2024 • 1

upvoted an article 9 days ago

view article

Article

Falcon Perception

• 

Apr 1

•

67

updated a dataset 12 days ago

zlab-princeton/VisionFoundry-10K

Viewer • Updated 12 days ago • 2 • 687 • 3

commented a paper 19 days ago

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Paper • 2604.09531 • Published about 1 month ago • 8 •

2

liked a model 19 days ago

ByteDance-Seed/BAGEL-7B-MoT

Any-to-Any • 15B • Updated Jan 9 • 3.46k • 1.2k

updated a collection 23 days ago

VisionFoundry

Collection

2 items • Updated 23 days ago • 1

upvoted a collection 28 days ago

VisionFoundry

Collection

2 items • Updated 23 days ago • 1

updated a collection 28 days ago

VisionFoundry

Collection

2 items • Updated 23 days ago • 1

liked a dataset 28 days ago

zlab-princeton/VisionFoundry-10K

Viewer • Updated 12 days ago • 2 • 687 • 3

upvoted a paper 28 days ago

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Paper • 2604.09531 • Published about 1 month ago • 8

liked a dataset about 1 month ago

songdj/CML-Bench

Preview • Updated May 16, 2025 • 70 • 2

published a dataset about 1 month ago

zlab-princeton/VisionFoundry-10K

Viewer • Updated 12 days ago • 2 • 687 • 3

upvoted a paper 3 months ago

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Paper • 2602.07026 • Published Feb 2 • 140

liked a Space 3 months ago

Running on CPU Upgrade

Agents

1.66k

Omni Image Editor

🖼

1.66k

Image edit, text to image, image upscale, remove watermark