CodeGoat24

UnifiedReward-2.0-qwen-7B We are actively gathering feedback from the community to improve our models. We welcome your input and encourage you to stay updated through our repository!! 🔥🔥🔥 We release UnifiedReward-2.0-qwen-[3b/7b/32b/72b]. This version introduces several new capabilities: >1. Pairwise scoring for image and video generation assessment on Alignment, Coherence, Style dimensions. > >2. Pointwise scoring for image and video generation assessment on Alignment, Coherence/Physics, Style dimensions. Welcome to try the latest version, and the inference code is available at `here`. `UnifiedReward-2.0-qwen-7b` is the first unified reward model based on Qwen/Qwen2.5-VL-7B-Instruct for multimodal understanding and generation assessment, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang | Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding | :-----: | :-----: |:-----: |:-----: | :-----: | :-----: | | PickScore |Point | √ | | || | HPS | Point | √ | ||| | ImageReward | Point| √| ||| | LLaVA-Critic | Pair/Point | | √ ||| | IXC-2.5-Reward | Pair/Point | | √ ||√| | VideoScore | Point | | |√ || | LiFT | Point | | |√| | | VisionReward | Point |√ | |√|| | VideoReward | Point | | |√ || | UnifiedReward (Ours) | Pair/Point | √ | √ |√|√|

`Unified-Reward-7b-v1.5` is the enhanced version of Unified-Reward-7b based on LLaVA-OneVision-7b, the first unified reward model for multimodal understanding and generation assessment, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang 🔥 News [2025/10/23] 🔥🔥🔥 We release UnifiedReward-Edit-[3b/7b/32b/72b], a unified reward model for both Text-to-Image and Image-to-Image generation trained on approximately 700K unified image generation and editing reward data!! For image editing reward task, our models support: >1. Pairwise Rank — directly judge which of two edited images is better. > >2. Pairwise Score — assign a separate score to each image in a pair. > >3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality. 🚀 The image editing reward inference code is available at `UnifiedReward-Edit/` directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from EditScore and EditReward and will be released soon. We sincerely appreciate all contributors!! [2025/9/25] 🔥🔥🔥 We release UnifiedReward-2.0-qwen-[3b/7b/32b/72b]. This version introduces several new capabilities: > >1. Pairwise scoring for image and video generation assessment on Alignment, Coherence, Style dimensions. > >2. Pointwise scoring for image and video generation assessment on Alignment, Coherence/Physics, Style dimensions. > The added inference code is available at `inferenceqwen/UnifiedReward-2.0-inference` directory. The newly added training data has been released here 😊. [2025/4/16] 🔥🔥 We updated the `UnifiedReward-7B-v1.5` by introducing pointwise scoring for generated images across three dimensions: alignment, coherence, and style, each rated on a continuous scale from 1 to 5. 1. Alignment quantifies how well an image matches its prompt. 2. Coherence assesses the logical consistency of the image and the absence of artifacts or visual glitches. 3. Style reflects the visual appeal of the image, independent of the prompt. | Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding | :-----: | :-----: |:-----: |:-----: | :-----: | :-----: | | PickScore |Point | √ | | || | HPS | Point | √ | ||| | ImageReward | Point| √| ||| | LLaVA-Critic | Pair/Point | | √ ||| | IXC-2.5-Reward | Pair/Point | | √ ||√| | VideoScore | Point | | |√ || | LiFT | Point | | |√| | | VisionReward | Point |√ | |√|| | VideoReward | Point | | |√ || | UnifiedReward (Ours) | Pair/Point | √ | √ |√|√| Quick Start All pair rank and point score inference codes are provided in our github. We take image understanding assessment as example here: ~~~python pip install git+https://github.com/LLaVA-VL/LLaVA-NeXT.git from llava.model.builder import loadpretrainedmodel from llava.mmutils import getmodelnamefrompath, processimages, tokenizerimagetoken from llava.constants import IMAGETOKENINDEX, DEFAULTIMAGETOKEN, DEFAULTIMSTARTTOKEN, DEFAULTIMENDTOKEN, IGNOREINDEX from llava.conversation import convtemplates, SeparatorStyle from PIL import Image import requests import copy import torch warnings.filterwarnings("ignore") pretrained = "CodeGoat24/UnifiedReward-7b-v1.5" modelname = "llavaqwen" device = "cuda" devicemap = "auto" tokenizer, model, imageprocessor, maxlength = loadpretrainedmodel(pretrained, None, modelname, devicemap=devicemap) # Add any other thing you want to pass in llavamodelargs url = "https://github.com/LLaVA-VL/blog/blob/main/2024-10-03-llava-critic/static/images/criticimgseven.png?raw=True" image = Image.open(requests.get(url, stream=True).raw) imagetensor = processimages([image], imageprocessor, model.config) imagetensor = [image.to(dtype=torch.float16, device=device) for image in imagetensor] convtemplate = "qwen15" # Make sure you use correct chat template for different models pairwise ranking criticprompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of the answers provided by a Large Multimodal Model (LMM). Determine which answer is better and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe first response: [The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.]\nThe second response: [This is a handwritten number seven.]\nASSISTANT:\n" pointwise scoring criticprompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of answer answers provided by a Large Multimodal Model (LMM). Score the response out of 100 and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe LMM response: [This is a handwritten number seven.]\nASSISTANT:\n " question = DEFAULTIMAGETOKEN + "\n" + criticprompt conv = copy.deepcopy(convtemplates[convtemplate]) conv.appendmessage(conv.roles[0], question) conv.appendmessage(conv.roles[1], None) promptquestion = conv.getprompt() inputids = tokenizerimagetoken(promptquestion, tokenizer, IMAGETOKENINDEX, returntensors="pt").unsqueeze(0).to(device) imagesizes = [image.size] cont = model.generate( inputids, images=imagetensor, imagesizes=imagesizes, dosample=False, temperature=0, maxnewtokens=4096, ) textoutputs = tokenizer.batchdecode(cont, skipspecialtokens=True) print(textoutputs[0]) ~~~

UnifiedReward-2.0-qwen-32B We are actively gathering feedback from the community to improve our models. We welcome your input and encourage you to stay updated through our repository!! 🔥🔥🔥 We release UnifiedReward-2.0-qwen-[3b/7b/32b/72b]. This version introduces several new capabilities: >1. Pairwise scoring for image and video generation assessment on Alignment, Coherence, Style dimensions. > >2. Pointwise scoring for image and video generation assessment on Alignment, Coherence/Physics, Style dimensions. Welcome to try the latest version, and the inference code is available at `here`. `UnifiedReward-2.0-qwen-32b` is the first unified reward model based on Qwen/Qwen2.5-VL-32B-Instruct for multimodal understanding and generation assessment, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang | Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding | :-----: | :-----: |:-----: |:-----: | :-----: | :-----: | | PickScore |Point | √ | | || | HPS | Point | √ | ||| | ImageReward | Point| √| ||| | LLaVA-Critic | Pair/Point | | √ ||| | IXC-2.5-Reward | Pair/Point | | √ ||√| | VideoScore | Point | | |√ || | LiFT | Point | | |√| | | VisionReward | Point |√ | |√|| | VideoReward | Point | | |√ || | UnifiedReward (Ours) | Pair/Point | √ | √ |√|√|

UnifiedReward-2.0-qwen-3B We are actively gathering feedback from the community to improve our models. We welcome your input and encourage you to stay updated through our repository!! 🔥🔥🔥 We release UnifiedReward-2.0-qwen-[3b/7b/32b/72b]. This version introduces several new capabilities: >1. Pairwise scoring for image and video generation assessment on Alignment, Coherence, Style dimensions. > >2. Pointwise scoring for image and video generation assessment on Alignment, Coherence/Physics, Style dimensions. Welcome to try the latest version, and the inference code is available at `here`. `UnifiedReward-2.0-qwen-3b` is the first unified reward model based on Qwen/Qwen2.5-VL-3B-Instruct for multimodal understanding and generation assessment, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang | Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding | :-----: | :-----: |:-----: |:-----: | :-----: | :-----: | | PickScore |Point | √ | | || | HPS | Point | √ | ||| | ImageReward | Point| √| ||| | LLaVA-Critic | Pair/Point | | √ ||| | IXC-2.5-Reward | Pair/Point | | √ ||√| | VideoScore | Point | | |√ || | LiFT | Point | | |√| | | VisionReward | Point |√ | |√|| | VideoReward | Point | | |√ || | UnifiedReward (Ours) | Pair/Point | √ | √ |√|√|

Unified-Reward-7B We are actively gathering feedback from the community to improve our models. We welcome your input and encourage you to stay updated through our repository! `Unified-Reward-7b` is the first unified reward model for multimodal understanding and generation assessment based on LLaVA-OneVision-7b, enabling both pairwise ranking and pointwise scoring, which can be employed for vision model preference alignment. For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang 🔥 News [2025/10/23] 🔥🔥🔥 We release UnifiedReward-Edit-[3b/7b/32b/72b], a unified reward model for both Text-to-Image and Image-to-Image generation trained on approximately 700K unified image generation and editing reward data!! For image editing reward task, our models support: >1. Pairwise Rank — directly judge which of two edited images is better. > >2. Pairwise Score — assign a separate score to each image in a pair. > >3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality. 🚀 The image editing reward inference code is available at `UnifiedReward-Edit/` directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from EditScore and EditReward and will be released soon. We sincerely appreciate all contributors!! [2025/9/25] 🔥🔥🔥 We release UnifiedReward-2.0-qwen-[3b/7b/32b/72b]. This version introduces several new capabilities: > >1. Pairwise scoring for image and video generation assessment on Alignment, Coherence, Style dimensions. > >2. Pointwise scoring for image and video generation assessment on Alignment, Coherence/Physics, Style dimensions. > The added inference code is available at `inferenceqwen/UnifiedReward-2.0-inference` directory. The newly added training data has been released here 😊. | Reward Model | Method| Image Generation | Image Understanding | Video Generation | Video Understanding | :-----: | :-----: |:-----: |:-----: | :-----: | :-----: | | PickScore |Point | √ | | || | HPS | Point | √ | ||| | ImageReward | Point| √| ||| | LLaVA-Critic | Pair/Point | | √ ||| | IXC-2.5-Reward | Pair/Point | | √ ||√| | VideoScore | Point | | |√ || | LiFT | Point | | |√| | | VisionReward | Point |√ | |√|| | VideoReward | Point | | |√ || | UnifiedReward (Ours) | Pair/Point | √ | √ |√|√| Quick Start All pair rank and point score inference codes are provided in our github. We take image understanding assessment as example here: ~~~python pip install git+https://github.com/LLaVA-VL/LLaVA-NeXT.git from llava.model.builder import loadpretrainedmodel from llava.mmutils import getmodelnamefrompath, processimages, tokenizerimagetoken from llava.constants import IMAGETOKENINDEX, DEFAULTIMAGETOKEN, DEFAULTIMSTARTTOKEN, DEFAULTIMENDTOKEN, IGNOREINDEX from llava.conversation import convtemplates, SeparatorStyle from PIL import Image import requests import copy import torch warnings.filterwarnings("ignore") pretrained = "CodeGoat24/UnifiedReward-7b" modelname = "llavaqwen" device = "cuda" devicemap = "auto" tokenizer, model, imageprocessor, maxlength = loadpretrainedmodel(pretrained, None, modelname, devicemap=devicemap) # Add any other thing you want to pass in llavamodelargs url = "https://github.com/LLaVA-VL/blog/blob/main/2024-10-03-llava-critic/static/images/criticimgseven.png?raw=True" image = Image.open(requests.get(url, stream=True).raw) imagetensor = processimages([image], imageprocessor, model.config) imagetensor = [image.to(dtype=torch.float16, device=device) for image in imagetensor] convtemplate = "qwen15" # Make sure you use correct chat template for different models pairwise ranking criticprompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of the answers provided by a Large Multimodal Model (LMM). Determine which answer is better and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe first response: [The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.]\nThe second response: [This is a handwritten number seven.]\nASSISTANT:\n" pointwise scoring criticprompt = "Given an image and a corresponding question, please serve as an unbiased and fair judge to evaluate the quality of answer answers provided by a Large Multimodal Model (LMM). Score the response out of 100 and explain your reasoning with specific details. Your task is provided as follows:\nQuestion: [What this image presents?]\nThe LMM response: [This is a handwritten number seven.]\nASSISTANT:\n " question = DEFAULTIMAGETOKEN + "\n" + criticprompt conv = copy.deepcopy(convtemplates[convtemplate]) conv.appendmessage(conv.roles[0], question) conv.appendmessage(conv.roles[1], None) promptquestion = conv.getprompt() inputids = tokenizerimagetoken(promptquestion, tokenizer, IMAGETOKENINDEX, returntensors="pt").unsqueeze(0).to(device) imagesizes = [image.size] cont = model.generate( inputids, images=imagetensor, imagesizes=imagesizes, dosample=False, temperature=0, maxnewtokens=4096, ) textoutputs = tokenizer.batchdecode(cont, skipspecialtokens=True) print(textoutputs[0]) ~~~

UnifiedReward-Edit-qwen-32B [2025/10/23] 🔥🔥🔥 We release UnifiedReward-Edit-32b, a unified reward model for both Text-to-Image and Image-to-Image generation!! For image editing reward task, our models support: >1. Pairwise Rank — directly judge which of two edited images is better. > >2. Pairwise Score — assign a separate score to each image in a pair. > >3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality. 🚀 The image editing reward inference code is available at `UnifiedReward-Edit/` directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from EditScore and EditReward and will be released soon. We sincerely appreciate all contributors!! For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

UnifiedReward-Edit-qwen-7B [2025/10/23] 🔥🔥🔥 We release UnifiedReward-Edit-7b, a unified reward model for both Text-to-Image and Image-to-Image generation!! For image editing reward task, our models support: >1. Pairwise Rank — directly judge which of two edited images is better. > >2. Pairwise Score — assign a separate score to each image in a pair. > >3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality. 🚀 The image editing reward inference code is available at `UnifiedReward-Edit/` directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from EditScore and EditReward and will be released soon. We sincerely appreciate all contributors!! For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang

This model is tailored for offline T2I model evaluation on UniGenBench, which achieves an average accuracy of 94% compared to evaluations by Gemini 2.5 Pro. Feel free to use this model to assess and compare the performance of your models. For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2508.20751 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/Pref-GRPO - 🤗 UniGenBench: https://github.com/CodeGoat24/UniGenBench - 🤗 Leaderboard: https://huggingface.co/spaces/CodeGoat24/UniGenBenchLeaderboard - 👋 Point of Contact: Yibin Wang

UnifiedReward-Edit-qwen-7B [2025/10/23] 🔥🔥🔥 We release UnifiedReward-Edit-3b, a unified reward model for both Text-to-Image and Image-to-Image generation!! For image editing reward task, our models support: >1. Pairwise Rank — directly judge which of two edited images is better. > >2. Pairwise Score — assign a separate score to each image in a pair. > >3. Pointwise Score — rate a single image on two axes: instruction-following and overall image quality. 🚀 The image editing reward inference code is available at `UnifiedReward-Edit/` directory, while T2I inference code is unchanged from previous models. The editing training data is preprocessed from EditScore and EditReward and will be released soon. We sincerely appreciate all contributors!! For further details, please refer to the following resources: - 📰 Paper: https://arxiv.org/pdf/2503.05236 - 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/ - 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a - 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede - 👋 Point of Contact: Yibin Wang