Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.
hub Canonical reference
"Your output must be a single JSON object.\n\n
Canonical reference. 80% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 12representative citing papers
UniPath adaptively models coordination-path diversity in unified multimodal models by training a path-conditioned executor and using a lightweight planner for input-dependent selection, improving performance over fixed strategies.
Unified multimodal models exhibit pseudo-unification due to modality-asymmetric entropy encoding and pattern-split responses between text and image generation.
RefineAnything is a multimodal diffusion model using Focus-and-Refine crop-and-resize with blended paste-back to achieve high-fidelity local image refinement and near-perfect background preservation.
A generative reconstruction algorithm turns video into editable text prompts, enabling text-driven reauthoring as shown in a creator study that identified use cases such as virtual reshooting and tensions around coherence and creative alignment.
AIA loss teaches unified multimodal models task-specific cross-modal attention patterns to reduce conflicts between image understanding and generation without architecture decoupling.
Semantic Generative Tuning uses image segmentation as a generative proxy to align misaligned representation spaces in unified multimodal models and improve both perception and generative layout fidelity.
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.
-
UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning
UniPath adaptively models coordination-path diversity in unified multimodal models by training a path-conditioned executor and using a lightweight planner for input-dependent selection, improving performance over fixed strategies.
-
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Unified multimodal models exhibit pseudo-unification due to modality-asymmetric entropy encoding and pattern-split responses between text and image generation.
-
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
RefineAnything is a multimodal diffusion model using Focus-and-Refine crop-and-resize with blended paste-back to achieve high-fidelity local image refinement and near-perfect background preservation.
-
Rewriting Video: Text-Driven Reauthoring of Video Footage
A generative reconstruction algorithm turns video into editable text prompts, enabling text-driven reauthoring as shown in a creator study that identified use cases such as virtual reshooting and tensions around coherence and creative alignment.
-
AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model
AIA loss teaches unified multimodal models task-specific cross-modal attention patterns to reduce conflicts between image understanding and generation without architecture decoupling.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning uses image segmentation as a generative proxy to align misaligned representation spaces in unified multimodal models and improve both perception and generative layout fidelity.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.
-
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
-
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.