Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models
Paper
•
2505.24164
•
Published
Xiangtai Li
LXT
AI & ML interests
Computer Vision, Multi-Modal Understanding, Generative AI
Recent Activity
authored
a paper
18 days ago
Mixed-R1: Unified Reward Perspective For Reasoning Capability in
Multimodal Large Language Models
authored
a paper
18 days ago
UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
authored
a paper
18 days ago
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and
Methodology
Organizations
authored
3
papers
18 days ago
upvoted
a
paper
18 days ago
updated
3
datasets
19 days ago
updated
a
dataset
20 days ago
updated
2
models
20 days ago
published
a
model
20 days ago
upvoted
3
papers
26 days ago
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper
•
2506.24119
•
Published
•
46
Ovis-U1 Technical Report
Paper
•
2506.23044
•
Published
•
60
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper
•
2507.01006
•
Published
•
200
liked
a
model
27 days ago
upvoted
a
paper
28 days ago
authored
4
papers
about 2 months ago
OmniAudio: Generating Spatial Audio from 360-Degree Video
Paper
•
2504.14906
•
Published
Towards Semantic Equivalence of Tokenization in Multimodal LLM
Paper
•
2406.05127
•
Published
So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection
Paper
•
2505.18660
•
Published
•
1
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
Paper
•
2505.23727
•
Published
•
4