IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment | Paper Citation Record

Observation 22783057-56b5-4371-a524-5660c948e57e · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.767912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1cbd9461-4551-4436-a93b-1bb8faa5d85d · outbound

This paper cites Blended diffusion for text-driven editing of natural images.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Blended diffusion for text-driven editing of natural images

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 828af531-1d8a-4ba3-ae94-7a01499d656d · outbound

This paper cites Qwen2.5-VL Technical Report.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.749105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 085e34b3-0f8f-4e37-927b-a3cde53562c2 · outbound

This paper cites In- structpix2pix: Learning to follow image editing instructions.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment In- structpix2pix: Learning to follow image editing instructions

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b22ef4-5c0c-432d-8fd1-430c3bcfbe64 · outbound

This paper cites Learning photographic global tonal adjustment with a database of input / output image pairs.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Learning photographic global tonal adjustment with a database of input / output image pairs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d838f0-03ec-4a95-9afc-cd829d7674f4 · outbound

This paper cites PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:37:22.751704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a145489-045c-4a1b-8e0b-366b3a4d3595 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.743815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 949c4d8e-8bc2-479c-a9bc-6651e38f20a7 · outbound

This paper cites Conde, Zihao Lu, and Radu Timofte.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Conde, Zihao Lu, and Radu Timofte

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6c5c37-c205-435a-bff8-c756038841db · outbound

This paper cites Turboedit: Text-based image editing using few-step diffusion models, 2024.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Turboedit: Text-based image editing using few-step diffusion models, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f4c288d-89b7-4292-ab45-3910de06bfcb · outbound

This paper cites A survey on rag meeting llms: Towards retrieval-augmented large language models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment A survey on rag meeting llms: Towards retrieval-augmented large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b202c99-5069-44da-b508-fc92914a00be · outbound

This paper cites Guiding instruction-based image editing via multimodal large language models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Guiding instruction-based image editing via multimodal large language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316443c1-9d61-4415-91f2-fd2f2e294a59 · outbound

This paper cites Efficient tool use with chain-of-abstraction reasoning.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Efficient tool use with chain-of-abstraction reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce814a5e-38f2-4180-ad32-50b499d90842 · outbound

This paper cites ToolkenGPT: Augmenting frozen language models with massive tools via tool embeddings.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment ToolkenGPT: Augmenting frozen language models with massive tools via tool embeddings

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f362c9-9a8e-4029-b121-c05f8ba196d1 · outbound

This paper cites Prompt-to-Prompt Image Editing with Cross Attention Control.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Prompt-to-Prompt Image Editing with Cross Attention Control

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.770320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 44954527-50b0-4652-8c27-7d676d146a4e · outbound

This paper cites Exposure: A white-box photo post-processing framework.ACM Transactions on Graphics (TOG), 37(2): 1–17, 2018.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Exposure: A white-box photo post-processing framework.ACM Transactions on Graphics (TOG), 37(2): 1–17, 2018

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9490f7b-ea5d-4e7d-997d-38155e113495 · outbound

This paper cites PatchDPO: Patch-level dpo for finetuning-free personalized image generation.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment PatchDPO: Patch-level dpo for finetuning-free personalized image generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95103d4a-faa6-40e0-a5bf-044a4dd065bf · outbound

This paper cites Smartedit: Exploring complex instruction-based image editing with multimodal large language models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Smartedit: Exploring complex instruction-based image editing with multimodal large language models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d095e9f0-9b45-49ab-8b18-f420e6c5a514 · outbound

This paper cites Survey of hallucination in natural language generation.ACM Comput.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Survey of hallucination in natural language generation.ACM Comput

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd05d687-356f-4c24-baba-727f3ff3b23b · outbound

This paper cites Imagic: Text-based real image editing with diffusion models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Imagic: Text-based real image editing with diffusion models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd4e413-271a-4ae4-b177-301d85954c36 · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 805480fa-b98e-444d-8780-2ca17a026400 · outbound

This paper cites Auto-Encoding Variational Bayes.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Auto-Encoding Variational Bayes

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.760595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 13ce8fc4-281b-4c02-b6f9-a72d961cae54 · outbound

This paper cites Learning Action and Reasoning-Centric Image Editing from Videos and Simulations.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Learning Action and Reasoning-Centric Image Editing from Videos and Simulations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63cb8613-5690-4bb5-84e6-db036efccd6b · outbound

This paper cites Zhu, and Mengyue Wu.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Zhu, and Mengyue Wu

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6888f7b7-ab67-4df1-8ce3-0ad111c1bf3d · outbound

This paper cites Cliptone: Unsupervised learning for text-based image tone adjustment.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Cliptone: Unsupervised learning for text-based image tone adjustment

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f2f2ad8-e97d-45f1-af89-1ce3f4ec53af · outbound

This paper cites Unsupervised dense retrieval with relevance-aware contrastive pre-training.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unsupervised dense retrieval with relevance-aware contrastive pre-training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e460f7-960c-4d3b-9f5f-12f4e1dcc5f1 · outbound

This paper cites Api-bank: A comprehensive benchmark for tool-augmented llms.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Api-bank: A comprehensive benchmark for tool-augmented llms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c6f7c62-8035-4b69-bb03-08fb6b03b045 · outbound

This paper cites ROUGE: A package for automatic evaluation of summaries.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment ROUGE: A package for automatic evaluation of summaries

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8c96950-e9b2-46a8-9ce7-466c69c2afad · outbound

This paper cites JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:37:22.748004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d1c99573-59ed-4734-b556-524ee20a4492 · outbound

This paper cites ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment ToolNet: Connecting Large Language Models with Massive Tools via Tool Graph

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:37:22.767026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ee5b1006-0fa9-4be7-b821-38d74fdba0e4 · outbound

This paper cites Agentbench: Evaluating LLMs as agents.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Agentbench: Evaluating LLMs as agents

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 223e417a-7b67-4852-9c0c-1804c415c6b5 · outbound

This paper cites Controlllm: Augment language models with tools by searching on graphs.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Controlllm: Augment language models with tools by searching on graphs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05cfb4dc-f2ea-49f6-adcf-d82b0ea57728 · outbound

This paper cites Apigen: automated pipeline for generating verifiable and diverse function-calling datasets.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Apigen: automated pipeline for generating verifiable and diverse function-calling datasets

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e7542f9-e170-47a1-b4f9-5e56ed9054a1 · outbound

This paper cites Chameleon: Plug-and-play compositional reasoning with large language models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Chameleon: Plug-and-play compositional reasoning with large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8242116-bee0-43e3-a852-11a167beb8a0 · outbound

This paper cites Repaint: Inpainting using denoising diffusion probabilistic models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Repaint: Inpainting using denoising diffusion probabilistic models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed65fea-865b-4b68-bc82-90b3788ddb60 · outbound

This paper cites TOOLVERIFIER: Generalization to new tools via self-verification.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment TOOLVERIFIER: Generalization to new tools via self-verification

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9783f90e-49af-4fd6-b59e-8cf3ebb9f1ab · outbound

This paper cites SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.742180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b3146e09-f725-4e9e-b8d1-486d5cab5560 · outbound

This paper cites Null-text inversion for editing real images using guided diffusion models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Null-text inversion for editing real images using guided diffusion models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a5d0740-45f7-4cc5-bf9e-35fdc99c1e50 · outbound

This paper cites Webgpt: Browser-assisted question-answering with human feedback, 2022.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Webgpt: Browser-assisted question-answering with human feedback, 2022

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0404403-c102-4829-bc7c-5f61fcfd7f01 · outbound

This paper cites Introducing our latest image generation model in the api.https://openai.com/index/image- generation-api/, 2025.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Introducing our latest image generation model in the api.https://openai.com/index/image- generation-api/, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e526749-e79b-4ee1-8aea-45cbb64665d9 · outbound

This paper cites Introducing gpt-4.1 in the api.https : / / openai.com/index/gpt-4-1/, 2025.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Introducing gpt-4.1 in the api.https : / / openai.com/index/gpt-4-1/, 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31d7b864-65cc-46ff-8967-1d20ef6231c3 · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdb2672c-88ca-45e7-9a93-ffa2e8e73e0d · outbound

This paper cites Distort-and-recover: Color enhancement using deep reinforcement learning.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Distort-and-recover: Color enhancement using deep reinforcement learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3251990f-584b-48f9-90d4-e8af3f321dc4 · outbound

This paper cites Gonzalez.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Gonzalez

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0132dc0-6d35-4a3a-ad1b-4dbb8ac57de1 · outbound

This paper cites Toolink: Linking toolkit creation and using through chain-of-solving on open-source model.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Toolink: Linking toolkit creation and using through chain-of-solving on open-source model

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f17d73a-a355-4382-bda4-47af78fc8f51 · outbound

This paper cites ToolLLM: Facilitating large language models to master 16000+ real-world APIs.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment ToolLLM: Facilitating large language models to master 16000+ real-world APIs

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be7002a-1a24-43c9-a0a5-b4ca409dd0ff · outbound

This paper cites Towards completeness-oriented tool retrieval for large language models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Towards completeness-oriented tool retrieval for large language models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21beff9c-1d60-4c6a-a8d9-2542a54125e8 · outbound

This paper cites From exploration to mastery: Enabling LLMs to master tools via self-driven interactions.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment From exploration to mastery: Enabling LLMs to master tools via self-driven interactions

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9093b66f-d6ba-477c-a8cd-7313dcac9449 · outbound

This paper cites Learning transferable visual models from natural language supervision.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Learning transferable visual models from natural language supervision

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5142842b-68f1-403e-b4d1-88b50ea7d700 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.763012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3998f59f-e314-4e95-8e11-c8c5750169fa · outbound

This paper cites Multimodal diffusion transformer: Learning versatile behavior from multimodal goals.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Multimodal diffusion transformer: Learning versatile behavior from multimodal goals

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825998d3-adbf-4f4a-bfcf-738e8c898f89 · outbound

This paper cites High-resolution image synthesis with latent diffusion models, 2021.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment High-resolution image synthesis with latent diffusion models, 2021

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c80b4372-011e-4bb3-86a1-cbfff6e07c2d · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Toolformer: Language models can teach themselves to use tools

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8501c56a-7b97-4cc4-8e91-b79c7724c80c · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.759479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e3c226e6-cfbe-41f1-a890-01603fb0af72 · outbound

This paper cites Hugginggpt: solving ai tasks with chatgpt and its friends in hugging face.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Hugginggpt: solving ai tasks with chatgpt and its friends in hugging face

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dba284e-7321-499c-a584-f16fea177680 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment HybridFlow: A Flexible and Efficient RLHF Framework

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.765503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3c07f04a-9525-4e79-a8ba-f1d9de36b71e · outbound

This paper cites A benchmark and baseline for language-driven image editing.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment A benchmark and baseline for language-driven image editing

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364af724-1528-4b7f-8f4d-c40ab62fefc8 · outbound

This paper cites Learning by planning: Language-guided global image editing.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Learning by planning: Language-guided global image editing

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34bd99a2-15fa-48f8-aec8-20ddeae0826d · outbound

This paper cites Spaceedit: Learning a unified editing space for open-domain image color editing.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Spaceedit: Learning a unified editing space for open-domain image color editing

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e4b7b3-6563-4928-bb8d-5b92e1e7d86b · outbound

This paper cites Learning to use tools via cooperative and interactive agents.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Learning to use tools via cooperative and interactive agents

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcee4440-1ef4-44ae-bf1f-332d1a3ec59a · outbound

This paper cites META-GUI: Towards multi-modal conversational agents on mobile GUI.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment META-GUI: Towards multi-modal conversational agents on mobile GUI

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 736a4a30-cdf3-4b8e-a6a3-bc09dfe859a0 · outbound

This paper cites Vipergpt: Visual inference via python execution for reasoning.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Vipergpt: Visual inference via python execution for reasoning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4d9b295-2dd9-42b3-a9be-db3710fe23c5 · outbound

This paper cites Qwen3 technical report, 2025.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Qwen3 technical report, 2025

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889f3fbd-6169-4150-94b3-92377e48bd07 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.745150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 11899da8-9574-4f54-97a3-5b2e46e91919 · outbound

This paper cites GenArtist: Multimodal llm as an agent for unified image generation and editing.Advances in Neural Information Processing Systems, 37:128374–128395, 2024.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment GenArtist: Multimodal llm as an agent for unified image generation and editing.Advances in Neural Information Processing Systems, 37:128374–128395, 2024

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c73267bc-2073-498b-b906-c9cf5822ddf2 · outbound

This paper cites Visual chatgpt: Talking, drawing and editing with visual foundation models, 2023.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Visual chatgpt: Talking, drawing and editing with visual foundation models, 2023

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7508a97-8878-496e-986b-b8703aa0e51d · outbound

This paper cites Qwen-Image Technical Report.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Qwen-Image Technical Report

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:37:22.764238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5a6cc917-0964-4db4-8090-040e62a30c04 · outbound

This paper cites Alignment for efficient tool calling of large language models, 2025.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Alignment for efficient tool calling of large language models, 2025

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 783346bf-d85d-48ce-b82e-7c1302101647 · outbound

This paper cites Delusions of large language models, 2025.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Delusions of large language models, 2025

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89c89ef7-2c19-48b9-aa86-b36106ca637c · outbound

This paper cites Reducing tool hallucination via reliability alignment.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Reducing tool hallucination via reliability alignment

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c69069-f43f-41c7-b2f1-0fb14cfc14c1 · outbound

This paper cites Inversion-free image editing with language-guided diffusion models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Inversion-free image editing with language-guided diffusion models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2ebe8bd-e3eb-4088-872e-7601a2f337ac · outbound

This paper cites Paint by example: Exemplar-based image editing with diffusion models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Paint by example: Exemplar-based image editing with diffusion models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a6b12d-2461-4477-b742-7d2d09a92640 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment React: Synergizing reasoning and acting in language models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 099cccd6-ef55-44ac-890a-648737ffe302 · outbound

This paper cites Craft: Customizing llms by creating and retrieving from specialized toolsets.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Craft: Customizing llms by creating and retrieving from specialized toolsets

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea3e250c-5d09-4475-aef1-fe03fa6868f6 · outbound

This paper cites Socratic models: Composing zero-shot multimodal reasoning with language.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Socratic models: Composing zero-shot multimodal reasoning with language

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22f8164f-996b-4e7a-8269-282d087277b5 · outbound

This paper cites UFO: A UI-Focused Agent for Windows OS Interaction.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment UFO: A UI-Focused Agent for Windows OS Interaction

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:37:22.762003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1391b8a8-9597-4f20-bacd-6b3d809b26db · outbound

This paper cites Magicbrush: A manually annotated dataset for instruction-guided image editing.Advances in Neural Information Processing Systems, 36:31428–31449, 2023.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Magicbrush: A manually annotated dataset for instruction-guided image editing.Advances in Neural Information Processing Systems, 36:31428–31449, 2023

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1059ea3-8366-40da-9d89-c5c5d78c215c · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2994b04-b565-4e7b-a03a-f540c4998e92 · outbound

This paper cites Ultraedit: Instruction-based fine-grained image editing at scale.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Ultraedit: Instruction-based fine-grained image editing at scale

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66aded7a-2ed6-4e9a-a9d6-81b0ddb1a70f · outbound

This paper cites ToolRerank: Adaptive and hierarchy-aware reranking for tool retrieval.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment ToolRerank: Adaptive and hierarchy-aware reranking for tool retrieval

Reference 79

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13cacf2-a6f0-4979-99f7-fe2ef9ff97b5 · outbound

This paper cites MobA: Multifaceted memory-enhanced adaptive planning for efficient mobile task automation.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment MobA: Multifaceted memory-enhanced adaptive planning for efficient mobile task automation

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3451d65e-4aa1-4814-9c53-59d903339299 · outbound

This paper cites brighter but less col- orful.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment brighter but less col- orful

Reference 81

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4d8b33-c6af-46b0-a055-2da166ad0537 · outbound

This paper cites "", 3: ".

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment "", 3: "

Reference 86

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d045dd79-05cf-472a-a5bc-e6e30a731c65 · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e92da2-7b58-488c-b75f-b0457a4cc19e · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 88

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6367c36-ba85-4ce0-b657-de9085964e95 · outbound

This paper cites exposure.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment exposure

Reference 89

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf29bf5-e376-4ac5-bce5-b28997854721 · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 90

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aad811e9-a47a-49df-8344-400b8603d65f · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 91

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2b972f0-763c-4022-89ca-8b94e1d99c96 · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 92

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c5a58b5-23b6-4b7f-bcb2-82d32fa1919b · outbound

This paper cites an unresolved cited work.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment Unresolved cited work

Reference 93

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 027ac9b3-72cb-4240-8db9-9518ba3a1ee0 · outbound

This paper cites </think> """ System Prompt for Summary Reward You are an expert image editor.

IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment </think> """ System Prompt for Summary Reward You are an expert image editor

Reference 94

Resolution: unresolved; no resolver link, observed 2026-06-27T20:18:49.849794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers