RS-Gen proposes a plug-and-play agentic framework with a closed-loop reasoning mechanism that augments base image models to achieve SOTA results on WISE Verified and RISEBench.
hub Canonical reference
InstructPix2Pix: Learning to Follow Image Editing Instructions
Canonical reference. 71% of citing Pith papers cite this work as background.
23
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 5
baseline 1
method 1
citation-polarity summary
representative citing papers
V2V-Bench is a new 11-dimension benchmark for video-to-video generation that achieves 0.905 Spearman correlation with human judgments on six V2V-specific dimensions.
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
Matched benchmarking reveals FID misleads in few-step regimes under CFG, prompting CLIP-scaled and PickScore-scaled FID and IS variants for better semantic evaluation of one-step image generators.
DRFS is a new inversion-free editing technique for rectified flow models that models source-target velocity discrepancies and applies a time-dependent shift to improve fidelity and unify prior methods like DDS and FlowEdit.
IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.
ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.
OCL is a governance layer for LLM agents that cuts unsafe executions from 88% to near-zero and raises valid success from 12% to 96% in adversarial buyer-seller negotiations across frontier LLMs.
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
SimInsert is a training-free video object insertion technique that decouples the task into single-frame editing and semantic motion description, using image-to-video diffusion models with non-invasive guidance to achieve spatio-temporal coherence.
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
PhysEdit introduces adaptive reasoning depth and spatial masking to make image editing faster and more instruction-aligned without retraining the base model.
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
Hunyuan3D 2.0 scales flow-based diffusion transformers and texture synthesis models to generate high-resolution textured 3D assets that outperform prior state-of-the-art in geometry, alignment, and texture quality.
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
citing papers explorer
-
RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
RS-Gen proposes a plug-and-play agentic framework with a closed-loop reasoning mechanism that augments base image models to achieve SOTA results on WISE Verified and RISEBench.
-
V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation
V2V-Bench is a new 11-dimension benchmark for video-to-video generation that achieves 0.905 Spearman correlation with human judgments on six V2V-specific dimensions.
-
Towards Characterizing Scientific Image Utility and Upgradability
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Matched benchmarking reveals FID misleads in few-step regimes under CFG, prompting CLIP-scaled and PickScore-scaled FID and IS variants for better semantic evaluation of one-step image generators.
-
Delta Rectified Flow Sampling for Text-to-Image Editing
DRFS is a new inversion-free editing technique for rectified flow models that models source-target velocity discrepancies and applies a time-dependent shift to improve fidelity and unify prior methods like DDS and FlowEdit.
-
IdeaBlocks: Expressing and Reusing Divergent Intents for Graphic Design Exploration using Generative AI
IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.
-
Visual Instruction Tuning
LLaVA is trained on GPT-4 generated visual instruction data to achieve 85.1% relative performance to GPT-4 on synthetic multimodal tasks and 92.53% accuracy on Science QA.
-
Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems
OCL is a governance layer for LLM agents that cuts unsafe executions from 88% to near-zero and raises valid success from 12% to 96% in adversarial buyer-seller negotiations across frontier LLMs.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
-
SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
SimInsert is a training-free video object insertion technique that decouples the task into single-frame editing and semantic motion description, using image-to-video diffusion models with non-invasive guidance to achieve spatio-temporal coherence.
-
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
UniVL unifies vision and language into one mask-rendered input processed by an OCR backbone to condition diffusion models for spatially grounded image generation without a standalone text encoder.
-
Stylistic Attribute Control in Latent Diffusion Models
A technique for parametric stylistic control in latent diffusion models learns disentangled directions from synthetic datasets and applies them via guidance composition while preserving semantics.
-
PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning
PhysEdit introduces adaptive reasoning depth and spatial masking to make image editing faster and more instruction-aligned without retraining the base model.
-
PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
-
Scaling Robot Learning with Semantically Imagined Experience
Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.
-
ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.
-
Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
-
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Hunyuan3D 2.0 scales flow-based diffusion transformers and texture synthesis models to generate high-resolution textured 3D assets that outperform prior state-of-the-art in geometry, alignment, and texture quality.
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.