Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Paper • 2605.05781 • Published • 3
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Linear-Time Global Visual Modeling without Explicit Attention
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models
shuidi0020
submitted a
paper to Daily Papers 1 day ago
RuizeHe
submitted a
paper to Daily Papers 7 days ago
JiayiGuo821
submitted a
paper to Daily Papers 14 days ago
shenzhi-wang
authored 2
papers about 2 months ago
shenzhi-wang
submitted a
paper to Daily Papers about 2 months ago
andrewzh
authored 3
papers 3 months ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 190
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
Paper • 2507.14201 • Published • 2
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
Paper • 2510.14381 • Published • 1
shenzhi-wang
authored 2
papers 4 months ago
nzl-thu
submitted a
paper to Daily Papers 4 months ago
yifanpu001
authored a
paper 5 months ago
JiayiGuo821
authored 7
papers 7 months ago
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
Paper • 2305.16223 • Published
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
Paper • 2406.08850 • Published
Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
Paper • 2406.04295 • Published
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
Paper • 2408.05710 • Published • 2
Taming Rectified Flow for Inversion and Editing
Paper • 2411.04746 • Published
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
Paper • 2411.06959 • Published
IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
Paper • 2509.26231 • Published • 18