Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe generation remove harmful concepts from models but face several challenges: (1) They cannot instantly remove harmful or undesirable concepts (e.g., artist styles) without additional training. (2) Their safe generation capabilities depend on collected training data. (3) They alter model weights, risking degradation in quality for content unrelated to the targeted toxic concepts. To address these challenges, we propose SAFREE, a novel, training-free approach for safe text-to-image and video generation, that does not alter the model's weights. Specifically, we detect a subspace corresponding to a set of toxic concepts in the text embedding space and steer prompt token embeddings away from this subspace, thereby filtering out harmful content while preserving intended semantics. To balance the trade-off between filtering toxicity and preserving safe concepts, SAFREE incorporates a novel self-validating filtering mechanism that dynamically adjusts the denoising steps when applying the filtered embeddings. Additionally, we incorporate adaptive re-attention mechanisms within the diffusion latent space to selectively diminish the influence of features related to toxic concepts at the pixel level. By integrating filtering across both textual embedding and visual latent spaces, SAFREE ensures coherent safety checking, preserving the fidelity, quality, and safety of the generated outputs. Empirically, SAFREE achieves state-of-the-art performance in suppressing unsafe content in T2I generation (reducing it by 22% across 5 datasets) compared to other training-free methods and effectively filters targeted concepts, e.g., specific artist styles, while maintaining high-quality output. It also shows competitive results against training-based methods. We further extend SAFREE to various T2I backbones and T2V tasks, showcasing its flexibility and generalization. As generative AI rapidly evolves, SAFREE provides a robust and adaptable safeguard for ensuring safe visual generation.

Multimodal Large Language Models (MLLMs) excel at synthesizing key information from diverse sources.However, generating accurate and faithful multimodal summaries is challenging, primarily due to the lack of appropriate multimodal datasets for fine-tuning that meaningfully integrate textual and visual modalities.To address this gap, we present a new dataset specifically designed for image-text multimodal summarization, harnessing the capabilities of state-of-the-art MLLMs.We generate summaries from Wikipedia sections and corresponding images and evaluate them across text-based, visual and multimodal dimensions, employing reference-free metrics.To refine the dataset, we: (1) filter the MLLM-generated summaries by training a critic model on human annotations and using its predictions to remove low-quality summaries; (2) fine-tune the MLLM with the filtered high-quality summaries; (3) use the fine-tuned model in turn to regenerate the summaries.This self-refinement process notably improves summary quality, as measured by human judgments and automatic multimodal metrics, resulting in a valuable dataset for multimodal summarization research.1 * Work done as an intern at Amazon AGI. 1 The dataset is publicly available at https://github. com/amazon-science/refinesumm.The Italian wall lizard or ruin lizard (Podarcis siculus, from the Greek meaning agile and feet) is a species of lizard in the family Lacertidae.P. siculus is native to Bosnia and Herzegovina, Croatia, France, Italy, Serbia, Montenegro, Slovenia, and Switzerland, but has also been introduced to Spain, ....

Pretrained language models sometimes possess knowledge that we do not wish them to, including memorized personal information and knowledge that could be used to harm people. They can also output toxic or harmful text. To mitigate these safety and informational issues, we propose an attack-and-defense framework for studying the task of deleting sensitive information directly from model weights. We study direct edits to model weights because (1) this approach should guarantee that particular deleted information is never extracted by future prompt attacks, and (2) it should protect against whitebox attacks, which is necessary for making claims about safety/privacy in a setting where publicly available model weights could be used to elicit sensitive information. Our threat model assumes that an attack succeeds if the answer to a sensitive question is located among a set of B generated candidates, based on scenarios where the information would be insecure if the answer is among B candidates. Experimentally, we show that even state-of-the-art model editing methods such as ROME struggle to truly delete factual information from models like GPT-J, as our whitebox and blackbox attacks can recover “deleted” information from an edited model 38% of the time. These attacks leverage two key observations: (1) that traces of deleted information can be found in intermediate model hidden states, and (2) that applying an editing method for one question may not delete information across rephrased versions of the question. Finally, we provide new defense methods that protect against some extraction attacks, but we do not find a single universally effective defense method. Our results suggest that truly deleting sensitive information is a tractable but difficult problem, since even relatively low attack success rates have potentially severe implications for the deployment of language models in a world where individuals enjoy ownership of their personal data, a right to privacy, and safety from harmful model outputs.

While great strides have been taken in advancing the field of Human-Robot Interaction (HRI), challenges abound in understanding and improving how Autonomous Vehicles (AVs) will interact with and within society. Through this paper, the authors attempt to paint the picture of challenges unique to the study and advancement of interfaces between AVs and vulnerable road users (VRUs). In turn, these gaps in research highlight the opportunities for academia, industry, and public policy to collaborate and advance the state of the art of AV-VRU interaction, and the need for a dedicated forum for sharing insights across these various sectors.

Applications based on image retrieval require editing and associating in intermediate spaces that are representative of the high-level concepts like objects and their relationships rather than dense, pixel-level representations like RGB images or semantic-label maps. We focus on one such representation, scene graphs, and propose a novel scene expansion task where we enrich an input seed graph by adding new nodes (objects) and the corresponding relationships. To this end, we formulate scene graph expansion as a sequential prediction task involving multiple iterations of first predicting a new node and then predicting the set of relationships between the newly predicted node and previously chosen nodes in the graph. We propose and evaluate a sequencing strategy that retains the clustering patterns amongst nodes. In addition, we leverage external knowledge to train our graph generation model, enabling greater generalization of node predictions. Due to the inefficiency of existing maximum mean discrepancy (MMD) based metrics standard for graph generation problems, we design novel metrics that comprehensively evaluate different aspects of node and relation predictions. We conduct extensive experiments on Visual Genome and VRD datasets to evaluate the expanded scene graphs using the standard MMD based metrics, as well as our proposed metrics. We observe that the graphs generated by our method, GEMS, better represent the real distribution of the scene graphs compared with baseline methods like GraphRNN.

Pre-trained multilingual language models such as mBERT and XLM-R have demonstrated great potential for zero-shot cross-lingual transfer to low web-resource languages (LRL).However, due to limited model capacity, the large difference in the sizes of available monolingual corpora between high web-resource languages (HRL) and LRLs does not provide enough scope of co-embedding the LRL with the HRL, thereby affecting the downstream task performance of LRLs.In this paper, we argue that relatedness among languages in a language family along the dimension of lexical overlap may be leveraged to overcome some of the corpora limitations of LRLs.We propose Overlap BPE (OBPE), a simple yet effective modification to the BPE vocabulary generation algorithm which enhances overlap across related languages.Through extensive experiments on multiple NLP tasks and datasets, we observe that OBPE generates a vocabulary that increases the representation of LRLs via tokens shared with HRLs.This results in improved zero-shot transfer from related HRLs to LRLs without reducing HRL representation and accuracy.Unlike previous studies that dismissed the importance of token-overlap, we show that in the low-resource related language setting, token overlap matters.Synthetically reducing the overlap to zero can cause as much as a four-fold drop in zero-shot transfer accuracy.

Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil, Abhijeet Awasthi, Partha Talukdar, Sunita Sarawagi. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.