We chose the Google Search corpus [Luo et al., 2021] for our question-answering system as it provides good coverage of the knowledge needed and is publicly available. However, as noted by the authors of RA-VQA, additional knowledge bases may be required to answer some questions correctly. Future work may address the issue by improving the quality and expanding the coverage of knowledge. We do not perceive any immediate ethical concerns associated with the misuse of our proposed system. There is a possibility that the trained KB-VQA system might generate inappropriate or biased content as a result of the training data biases during LLM and LMM pre-training and fine-tuning.

Knowledge-based Visual Question Answering (KB-VQA) requires VQA systems to utilize knowledge from external knowledge bases to answer visually-grounded questions. Retrieval-Augmented Visual Question Answering (RA-VQA), a strong framework to tackle KB-VQA, first retrieves related documents with Dense Passage Retrieval (DPR) and then uses them to answer questions. This paper proposes Fine-grained Late-interaction Multi-modal Retrieval (FLMR) which significantly improves knowledge retrieval in RA-VQA. FLMR addresses two major limitations in RA-VQA's retriever: (1) the image representations obtained via image-to-text transforms can be incomplete and inaccurate and (2) relevance scores between queries and documents are computed with one-dimensional embeddings, which can be insensitive to finer-grained relevance. FLMR overcomes these limitations by obtaining image representations that complement those from the image-totext transforms using a vision model aligned with an existing text-based retriever through a simple alignment network. FLMR also encodes images and questions using multi-dimensional embeddings to capture finer-grained relevance between queries and documents. FLMR significantly improves the original RA-VQA retriever's PRRecall@5 by approximately 8%. Finally, we equipped RA-VQA with two state-of-the-art large multi-modal/language models to achieve 61% VQA score in the OK-VQA dataset.

We introduce an offline multi-agent reinforcement learning (offline MARL) framework that utilizes previously collected data without additional online data collection. Our method reformulates offline MARL as a sequence modeling problem and thus builds on top of the simplicity and scalability of the Transformer architecture. In the fashion of centralized training and decentralized execution, we propose to first train a teacher policy who has the privilege to access every agent's observations, actions, and rewards. After the teacher policy has identified and recombined the "good" behavior in the dataset, we create separate student policies and distill not only the teacher policy's features but also its structural relations among different agents' features to student policies. We show that our framework significantly improves performances on a range of tasks and outperforms state-of-the-art offline MARL baselines. Furthermore, we demonstrate that the proposed method has a better convergence rate, is more sample efficient, and is more robust to various demonstration qualities compared with baselines.

We chose the Google Search corpus [Luo et al., 2021] for our question-answering system as it provides good coverage of the knowledge needed and is publicly available. Therefore, it is advised to conduct an ethical review prior to deploying the system in live service. Table 1 shows the data statistics of the OK-VQA dataset. We build a DPR retriever as a baseline for FLMR. Equally contributed as the first author 37th Conference on Neural Information Processing Systems (NeurIPS 2023). The inner product search (supported by FAISS [Johnson et al., 2019]) is used to train and In answer generation, we use t5-large and Salesforce/blip2-flan-t5-xl.

Retrieval (DPR) and then uses them to answer questions.

Table 7 and Table 8 of this appendix report the evaluation of attacks with whitebox and blackbox knowledge, respectively, of the system from which the template is leaked (i.e., Table 7: Evaluation of attacks with whitebox knowledge of the system from which the template is leaked (i.e., It is noteworthy that generally, in training GANs (even in conditional GANs) a noise (e.g., from Gaussian distribution) is used in The samples of noise in the input help the generator to learn the distribution of the output space, and therefore help the generator network to generate outputs from the same distribution of real data. However, our method can also be used with other face generator networks. Let us consider the complete pipeline of our problem formulation as depicted in Figure 2 of the paper. During inference (i.e., attacking the target FR system), however, the generated high-resolution face Mitigation of such Attacks This paper demonstrates an important privacy and security threat to the state-of-the-art unprotected face recognition systems. Council, 2016], put legal obligations to protect biometric data as sensitive information. We build face recognition pipelines using Bob [Anjos et al., 2012, 2017] toolbox We have also cited the corresponding paper for each dataset.

No ground-truth foreground masks are used during the training.

As image generative models continue to increase not only in their fidelity but also in their ubiquity the development of tools that leverage direct interaction with their internal mechanisms in an interpretable way has received little attention In this work we introduce a system that allows users to develop a better understanding of the model through interaction and experimentation By giving users the ability to replace activation functions of a generative network with parametric ones and a way to set the parameters of these functions we introduce an alternative approach to control the networks output We demonstrate the use of our method on StyleGAN2 and BigGAN networks trained on FFHQ and ImageNet respectively.