No article text was recorded for this version.
vision-language feedback loop
Version 2 of 2395 papers540 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
- Blog: Interleaving Reasoning for Better Text-to-Image Generation
- Blog: Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
- Blog: Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback
- Blog: RECODE: Reasoning Through Code Generation for Visual Question Answering
- Blog: PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
- Blog: Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
- Blog: VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation
- Blog: Iterative Refinement Improves Compositional Image Generation
- Blog: CoFi-Dec: Hallucination-Resistant Decoding via Coarse-to-Fine Generative Feedback in Large Vision-Language Models
- Blog: ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
- Blog: MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
- Blog: SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model
- Blog: SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code
- Blog: Query2CAD: Generating CAD models using natural language queries
- Blog: LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions
- Blog: Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
- Blog: T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation
- Blog: Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
- Blog: PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
- Blog: TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models
- Blog: StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback
- Blog: Perception in Reflection
- Blog: See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers
- Blog: Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
- Blog: What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation
- Blog: IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web
- Blog: ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance
- Blog: Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek
- Blog: LiveFigure: Generating Editable Scientific Illustration with VLM Agents
- Blog: TTGen: Incorporating Test-time Scaling to Diffusion Models
- Blog: CoDA: Agentic Systems for Collaborative Data Visualization
- Blog: SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code
- Blog: IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
- Blog: Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection
- Blog: Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation
- Blog: DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework
- Blog: Code2Worlds: Empowering Coding LLMs for 4D World Generation
- Blog: Self-Evolving Visual Concept Library using Vision-Language Critics
- Blog: UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
- Blog: Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning
- Blog: Anywhere: A Multi-Agent Framework for Reliable and Diverse Foreground-Conditioned Image Inpainting
- Blog: Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
- Blog: ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model
- Blog: ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback
- Blog: Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG
- Blog: Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation
- Blog: Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation
- Blog: UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
- Blog: CityX: Controllable Procedural Content Generation for Unbounded 3D Cities
- Blog: FinSight: Towards Real-World Financial Deep Research
- Blog: Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
- Blog: RAISECity: A Multimodal Agent Framework for Reality-Aligned 3D World Generation at City-Scale
- Blog: Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
- Blog: Thinking with Generated Images
- Blog: VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
- Blog: CoFi-Dec: Hallucination-Resistant Decoding via Coarse-to-Fine Generative Feedback in Large Vision-Language Models
- Blog: CoMA: Compositional Human Motion Generation with Multi-modal Agents
- Blog: DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
- Blog: Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry
Showing 60 of 395 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_vision_language_feedback_loop_a145eecc,
title = {vision-language feedback loop},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/vision-language-feedback-loop/rdr_a145eecce2224aabb9be01b86d53a426},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_vision_language_feedback_loop_a145eecc_v2,
title = {vision-language feedback loop},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/vision-language-feedback-loop/rdr_a145eecce2224aabb9be01b86d53a426/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}