Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation
Paper
•
2504.17207
•
Published
•
23
Zedong Wang
ZedongWangAI
AI & ML interests
Computer Vision, Multi-task Learning, Multi-modal Learning.
Recent Activity
upvoted
a
paper
about 11 hours ago
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery
Simulation
upvoted
a
paper
about 23 hours ago
Token-Shuffle: Towards High-Resolution Image Generation with
Autoregressive Models
upvoted
a
paper
about 23 hours ago
Breaking the Modality Barrier: Universal Embedding Learning with
Multimodal LLMs
Organizations
ZedongWangAI's activity
upvoted
a
paper
about 11 hours ago
upvoted
2
papers
about 23 hours ago
upvoted
2
papers
23 days ago
commented
a
paper
23 days ago
authored
2
papers
24 days ago
commented
3
papers
24 days ago
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper
•
2504.00999
•
Published
•
83
•
7
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper
•
2504.00999
•
Published
•
83
•
7
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper
•
2504.00999
•
Published
•
83
•
7
updated
a
collection
24 days ago
upvoted
a
paper
24 days ago
updated
a
collection
24 days ago
upvoted
a
paper
24 days ago