Multimodal LLMs as Customized Reward Models for Text-to-Image Generation | Paper Citation Record

Observation 056a1e6a-beb3-4817-b201-201c4fffe76b · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:32.526329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eb2ab8a-9a25-4c24-aadd-539f4e16e3a0 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:32.634149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1414ac53-eb29-4751-a06b-8f3f69844a80 · outbound

This paper cites Qwen2.5-VL Technical Report.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:32.751253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e9eb8b-c2f4-4e4f-9905-3f8dce5d3266 · outbound

This paper cites A Note on the Inception Score.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation A Note on the Inception Score

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:32.829262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4616089-20a5-497c-8a4a-67aef162a28a · outbound

This paper cites Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:32.897882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a57abf-d454-4edd-97d9-20a2f7402118 · outbound

This paper cites Training Diffusion Models with Reinforcement Learning.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Training Diffusion Models with Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:32.955610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c9bb625-c517-49c5-a40f-a8c3e4d0db53 · outbound

This paper cites Rank analysis of incomplete block designs: I.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Rank analysis of incomplete block designs: I

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:44.693809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bb5a2d9f-8017-4cdd-8ae8-61688734c0a3 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.162969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed65cea-25c8-4a87-a108-28b39587f9d8 · outbound

This paper cites SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.250868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02c55c24-4378-4579-8a74-f34efdfec3c2 · outbound

This paper cites MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.346700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f92e954-ec8f-447b-a014-6cb2464831dd · outbound

This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.452384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe32db23-e6ac-4c04-a95c-a2c6e99d02ca · outbound

This paper cites The socio-moral image database (smid),.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation The socio-moral image database (smid),

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:44.450201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 62b1b304-f88a-48e3-a114-a693b7d5c173 · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.643754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f9e2686-3aa2-4027-9f15-d3df3ff8be4f · outbound

This paper cites Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.744321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78af6481-780c-46fc-b0f7-791cee9478e1 · outbound

This paper cites Diffusion models beat gans on image synthesis.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Diffusion models beat gans on image synthesis

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:33.829967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1490d63-88ed-496b-aa9e-9014014c8769 · outbound

This paper cites Cogview: Mastering text-to-image generation via transformers.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Cogview: Mastering text-to-image generation via transformers

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:44.159261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 52916587-4e53-4a68-838e-944fbb9d03f4 · outbound

This paper cites Dpok: Reinforcement learning for fine-tuning text-to-image diffu- sion models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Dpok: Reinforcement learning for fine-tuning text-to-image diffu- sion models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:43.900852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 34de7a70-025e-44a6-9eb6-2c9eec8e2305 · outbound

This paper cites Geneval: An object-focused framework for evaluating text- to-image alignment.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Geneval: An object-focused framework for evaluating text- to-image alignment

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:43.638002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 60ca7fe7-16c2-4966-bc17-8305b4f4f500 · outbound

This paper cites Generative adversarial networks.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Generative adversarial networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:43.359411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d8979830-9d36-44d0-be4c-f66261f68e20 · outbound

This paper cites LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.226626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93f16588-f141-461c-beb4-88fdcbfe6f57 · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.274450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 221cbe1b-c39c-48fa-b1f5-12875ac86735 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Gans trained by a two time-scale update rule converge to a local nash equilib- rium

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.347454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 175a9c86-8bea-49fc-b5ff-ec2393d1ae23 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Denoising dif- fusion probabilistic models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.455883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6bf3fea-02f6-44eb-904f-15421c7d9897 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation LoRA: Low-Rank Adaptation of Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.578707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 848fe526-4132-4bf4-9e22-842a315f02bf · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.709673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc91a6b-bbdc-4591-8105-4bfd5f909bf7 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Pick-a-pic: An open dataset of user preferences for text-to-image generation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:43.109881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4bf251e1-f89a-4031-8745-a2ac7ded0574 · outbound

This paper cites VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:34.950914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d72d80f3-ba3e-4c4d-9c51-5d707ddf2eb9 · outbound

This paper cites What matters when building vision-language models?.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation What matters when building vision-language models?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.047298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71df43e3-76ce-4791-a801-b71882b18abe · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:42.807225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bc9aae33-9a27-401b-b7c8-be632420679e · outbound

This paper cites T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.249132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94664539-1edf-4155-acf0-6690ccf5666b · outbound

This paper cites Remov- ing distributional discrepancies in captions improves image- text alignment.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Remov- ing distributional discrepancies in captions improves image- text alignment

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:42.539329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 337ed284-26b4-4f43-b34a-095d129c1003 · outbound

This paper cites Evaluating text-to-visual generation with image-to-text gen- eration.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Evaluating text-to-visual generation with image-to-text gen- eration

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:42.271746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0b495463-d938-487a-836d-29917f2f9c97 · outbound

This paper cites Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.526604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 485cd105-58bf-4858-b115-6c11111da2f0 · outbound

This paper cites Improved baselines with visual instruction tuning, 2023.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Improved baselines with visual instruction tuning, 2023

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:42.023960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0750e59b-d266-4b5c-be87-abf663dab75c · outbound

This paper cites Visual instruction tuning, 2023.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Visual instruction tuning, 2023

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:41.790950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e18fadd7-3903-415d-8b9c-58d5e539e4c0 · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:41.529889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d4a9139f-d60a-4b32-a7b7-4b4aaa609763 · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.785004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af03050d-fe22-4c9c-86de-850fb1ef8d9a · outbound

This paper cites Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.880961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90215b59-d14e-4456-8c68-0e470e90ac48 · outbound

This paper cites Simpo: Sim- ple preference optimization with a reference-free reward.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Simpo: Sim- ple preference optimization with a reference-free reward

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:41.318338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1d91967a-7d25-4f32-86be-571db2738094 · outbound

This paper cites Training language models to follow instructions with human feedback.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Training language models to follow instructions with human feedback

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.985916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dbeb8a1-6a9a-4e17-bca3-1bd6e508fc90 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:36.083635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19a5864c-3e88-4d4d-8c3a-5565a4ec0ab4 · outbound

This paper cites Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:41.061472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 486054fb-1c29-405f-a1e9-74cbe132e51b · outbound

This paper cites UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:36.257427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 498d6646-c498-490b-95c6-c800bcb74c8e · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Learning transferable visual models from natural language supervi- sion

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:36.362963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95dc7cc0-f7d0-40c6-b4f4-aca3578260c1 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Direct preference optimization: Your language model is secretly a reward model

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:40.824402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 607b8cf6-d085-4e66-8f7e-74768b3fca54 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Direct preference optimization: Your language model is secretly a reward model

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:40.561887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dc7536f8-7fcf-463d-90d7-e39f42ce4053 · outbound

This paper cites Zero-shot text-to-image generation.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Zero-shot text-to-image generation

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:40.280839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c52fbfde-6f70-4c49-9cd8-36c5ef12c567 · outbound

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

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation High-resolution image synthesis with latent diffusion models

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:40.038981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4d7867f7-2ff2-42e1-8576-59eb0668b5c0 · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Photorealistic text-to-image diffusion models with deep language understanding

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:39.835962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f0c300b8-ddfb-44bf-b455-1d9f0393f153 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:36.914296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce9b861-b945-4995-ba66-1d41e41b7056 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Proximal Policy Optimization Algorithms

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:36.988698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a326a054-deaf-4fbf-8f2f-962890284bd8 · outbound

This paper cites A General Framework for Inference-time Scaling and Steering of Diffusion Models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation A General Framework for Inference-time Scaling and Steering of Diffusion Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:37.089978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb5a6c6-185f-4428-8657-6b08bb29b32c · outbound

This paper cites an unresolved cited work.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:54:39.626966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 04f9475e-a2e7-4fcf-acdb-d64cd9abb94f · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Deep unsupervised learning using nonequilibrium thermodynamics

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:39.484015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation faaa401d-b7f0-4ec2-b1aa-a54f8cd4e031 · outbound

This paper cites Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:37.374599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6f6be9-143b-4030-8a6e-1d5888fb3122 · outbound

This paper cites EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:37.474204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf014844-e467-460e-99a7-964de4cccaef · outbound

This paper cites Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-06T12:54:38.472533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0d92521d-7af7-4991-839f-b0e355584ce3 · outbound

This paper cites HelpSteer2-Preference: Complementing Ratings with Preferences.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation HelpSteer2-Preference: Complementing Ratings with Preferences

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:37.619519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0649d742-b68a-404e-b33f-82115b5ade71 · outbound

This paper cites MLLM-as-a-Judge for Image Safety without Human Labeling.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation MLLM-as-a-Judge for Image Safety without Human Labeling

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:37.686456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47994f55-4f79-43be-96c8-6f0b8b3df90c · outbound

This paper cites Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:37.787465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55c643a1-c5da-4050-9945-d9ba9e50d216 · outbound

This paper cites Human preference score: Better aligning text- to-image models with human preference.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Human preference score: Better aligning text- to-image models with human preference

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:39.344930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 75506a12-6c51-49bb-ab43-87fb31752d09 · outbound

This paper cites Imagere- ward: Learning and evaluating human preferences for text- to-image generation.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Imagere- ward: Learning and evaluating human preferences for text- to-image generation

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:39.261401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3eaeffba-521a-4480-85fb-6f093aab3080 · outbound

This paper cites A normalized levenshtein distance metric.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation A normalized levenshtein distance metric

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:39.129080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3f3acc0d-51d8-422a-8f4f-e5647e7a1e6a · outbound

This paper cites When and why vision- language models behave like bags-of-words, and what to do about it? In The Eleventh International Conference on Learning Representations, 2023.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation When and why vision- language models behave like bags-of-words, and what to do about it? In The Eleventh International Conference on Learning Representations, 2023

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:38.984919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a5e53093-eb1b-4ff2-9218-0079c8c509a9 · outbound

This paper cites Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:38.169486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b42a0d17-7f87-4a78-8598-5098a9b2a63e · outbound

This paper cites Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:38.229729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb6d2b9e-4aab-478f-ba2d-91070b9da082 · outbound

This paper cites Towards language-free training for text-to-image generation.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation Towards language-free training for text-to-image generation

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:54:38.832890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers