paper-with-me

Papers

LLaVA-Critic: Learning to Evaluate Multimodal Models

2024-10-03 · CVPR 2025 1 · Tianyi Xiong, Xiyao Wang, Dong Guo, Qinghao Ye, Haoqi Fan, Quanquan Gu, Heng Huang, Chunyuan Li

We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator to assess performance across a wide range of multimodal tasks. LLaVA-Critic is trained using a high-quality critic instruction-following dataset that incorporates diverse evaluation criteria and scenarios. Our experiments demonstrate the model's effectiveness in two key areas: (1) LMM-as-a-Judge, where LLaVA-Critic provides reliable evaluation scores, performing on par with or surpassing GPT models on multiple evaluation benchmarks; and (2) Preference Learning, where it generates reward signals for preference learning, enhancing model alignment capabilities. This work underscores the potential of open-source LMMs in self-critique and evaluation, setting the stage for future research into scalable, superhuman alignment feedback mechanisms for LMMs.

📄 PDF Abstract BibTeX arXiv:2410.02712

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Weight Decay 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

2025-08-31 · Xiyao Wang, Chunyuan Li, Jianwei Yang, Kai Zhang 외 arxiv

In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which prod…

Reinforcement LearningVisual Reasoning

LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier

2025-02-05 · T. Chay-intr, Y. Chen, K. Viriyayudhakorn, T. Theeramunkong

We present LLaVAC, a method for constructing a classifier for multimodal sentiment analysis. This method leverages fine-tuning of the Large Language and Vision Assistant (LLaVA) to predict sentiment labels across both im…

Multimodal Sentiment AnalysisSentiment AnalysisSentiment Classification

LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing

2023-11-01 · Wei-Ge Chen, Irina Spiridonova, Jianwei Yang, Jianfeng Gao 외

LLaVA-Interactive is a research prototype for multimodal human-AI interaction. The system can have multi-turn dialogues with human users by taking multimodal user inputs and generating multimodal responses. Importantly, …

AllImage GenerationImage SegmentationSemantic Segmentation

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

2024-05-24 · Chunjiang Ge, Sijie Cheng, ZiMing Wang, Jiale Yuan 외

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating exc…

Visual Question Answering

Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety

2025-08-29 · Younggun Kim, Sirnam Swetha, Fazil Kagdi, Mubarak Shah arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body wei…