Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Paper • 2607.01191 • Published • 18
Zhejiang University
university
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
hongxingli
submitted a
paper to Daily Papers 11 days ago
sicloud
published a
model 28 days ago
sicloud
updated a
model about 1 month ago
YZCS
authored a
paper about 1 month ago
YZCS
submitted a
paper to Daily Papers about 1 month ago
lhy-zju
submitted a
paper to Daily Papers about 1 month ago
Yixuan-Ding-ZJU
submitted a
paper to Daily Papers about 1 month ago
Wanux
submitted a
paper to Daily Papers about 1 month ago
YZCS
authored a
paper about 1 month ago
YZCS
submitted a
paper to Daily Papers about 1 month ago
Z-MU-Z
submitted 2
papers to Daily Papers about 1 month ago
RL-2000
authored 8
papers about 1 month ago
Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt
Paper • 2403.11780 • Published
Accompanied Singing Voice Synthesis with Fully Text-controlled Melody
Paper • 2407.02049 • Published
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
Paper • 2408.16532 • Published • 50
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
Paper • 2409.13832 • Published • 1
MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization
Paper • 2410.12957 • Published • 8
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
Paper • 2409.15977 • Published • 2
StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
Paper • 2312.10741 • Published • 1
TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching
Paper • 2502.12572 • Published • 2