Unicorn: Text-Only Data Synthesis for Vision Language Model Training
Paper
•
2503.22655
•
Published
•
38
Siteng Huang
huangsiteng
AI & ML interests
vision-language models
Recent Activity
upvoted
a
paper
20 days ago
Unicorn: Text-Only Data Synthesis for Vision Language Model Training
authored
a paper
25 days ago
Exploring the Evolution of Physics Cognition in Video Generation: A
Survey
upvoted
a
paper
25 days ago
Exploring the Evolution of Physics Cognition in Video Generation: A
Survey
Organizations
None yet
huangsiteng's activity
upvoted
a
paper
20 days ago
authored
a
paper
25 days ago
upvoted
a
paper
25 days ago
commented
a
paper
25 days ago
authored
3
papers
4 months ago
Accelerating Diffusion Transformers with Token-wise Feature Caching
Paper
•
2410.05317
•
Published
Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration
Paper
•
2411.17686
•
Published
•
21
CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction
Paper
•
2412.06782
•
Published
•
7
upvoted
a
paper
4 months ago
commented
a
paper
4 months ago
upvoted
a
paper
5 months ago
commented
a
paper
5 months ago
authored
a
paper
7 months ago
upvoted
a
paper
7 months ago
commented
a
paper
7 months ago
liked
a
Space
about 1 year ago
authored
5
papers
about 1 year ago
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
Paper
•
2403.14520
•
Published
•
36
VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval
Paper
•
2211.12764
•
Published
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
Paper
•
2303.15230
•
Published
Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
Paper
•
2311.15841
•
Published
•
2
Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
Paper
•
2311.15773
•
Published
•
4