paper-with-me

Papers

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

2024-06-20 · Yuxuan Qiao, Haodong Duan, Xinyu Fang, Junming Yang, Lin Chen, Songyang Zhang, Jiaqi Wang, Dahua Lin, Kai Chen

Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is crucial for model refinement, despite the inherent difficulty due to the intertwined nature of seeing and reasoning in existing VLMs. To tackle this issue, we present Prism, an innovative framework designed to disentangle the perception and reasoning processes involved in visual question solving. Prism comprises two distinct stages: a perception stage that utilizes a VLM to extract and articulate visual information in textual form, and a reasoning stage that formulates responses based on the extracted visual information using a Large Language Model (LLM). This modular design enables the systematic comparison and assessment of both proprietary and open-source VLM for their perception and reasoning strengths. Our analytical framework provides several valuable insights, underscoring Prism's potential as a cost-effective solution for vision-language tasks. By combining a streamlined VLM focused on perception with a powerful LLM tailored for reasoning, Prism achieves superior results in general vision-language tasks while substantially cutting down on training and operational expenses. Quantitative evaluations show that Prism, when configured with a vanilla 2B LLaVA and freely accessible GPT-3.5, delivers performance on par with VLMs $10 \times$ larger on the rigorous multimodal benchmark MMStar. The project is released at: https://github.com/SparksJoe/Prism.

📄 PDF Abstract BibTeX arXiv:2406.14544

Code (1)

sparksjoe/prism 공식 구현 pytorch

Tasks

Language ModellingLarge Language Model

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 &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense

2026-01-27 · Binyan Xu, Fan Yang, Xilin Dai, Di Tang 외 arxiv

Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model repairing or input robustness, yet these a…

VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer

2026-05-27 · Rui Lin, Chuanming Wang, Huadong Ma arxiv

With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding \emph{\ie} image-to-video transfer learning has become a dominant paradigm. To achieve s…

Transfer Learning

PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation

2025-12-05 · Shima Imani, Seungwhan Moon, Adel Ahmadyan, Lu Zhang 외 arxiv

Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains demand conceptual understanding, symbolic rea…

Program Synthesis

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection

2025-07-11 · Mahdiyar Molahasani, Azadeh Motamedi, Michael Greenspan, Il-Min Kim 외 arxiv

We introduce Projection-based Reduction of Implicit Spurious bias in vision-language Models (PRISM), a new data-free and task-agnostic solution for bias mitigation in VLMs like CLIP. VLMs often inherit and amplify biases…

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality

2025-08-26 · Nanxi Li, Zhengyue Zhao, G. Edward Suh, Marco Pavone 외 arxiv

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require de…