yusong hu

songsongh's activity

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

upvoted a paper 12 days ago

Depth Anything at Any Condition

Paper • 2507.01634 • Published 13 days ago • 46

upvoted a paper 15 days ago

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Paper • 2506.21862 • Published 18 days ago • 35

upvoted 2 papers about 2 months ago

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs

Paper • 2505.21327 • Published May 27 • 83

NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification

Paper • 2505.16938 • Published May 22 • 119

upvoted a paper 3 months ago

VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning

Paper • 2504.07960 • Published Apr 10 • 49

upvoted a paper 8 months ago

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Paper • 2411.10442 • Published Nov 15, 2024 • 81