Attribution methods shed light on the explainability of data-driven approaches such as deep learning models by revealing the most contributing features to decisions that have been made. A widely accepted way of deriving feature attributions is to analyze the gradients of the target function with respect to input features. Analysis of gradients requires full access to the target system, meaning that solutions of this kind treat the target system as a white-box. However, the white-box assumption may be untenable due to security and safety concerns, thus limiting their practical applications. As an answer to the limited flexibility, this paper presents GEEX (gradient-estimation-based explanation), an explanation method that delivers gradient-like explanations under a black-box setting. Furthermore, we integrate the proposed method with a path method. The resulting approach iGEEX (integrated GEEX) satisfies the four fundamental axioms of attribution methods: sensitivity, insensitivity, implementation invariance, and linearity. With a focus on image data, the exhaustive experiments empirically show that the proposed methods outperform state-of-the-art black-box methods and achieve competitive performance compared to the ones with full access.

This paper surveys the current state of the art in document automation (DA). The objective of DA is to reduce the manual effort during the generation of documents by automatically creating and integrating input from different sources and assembling documents conforming to defined templates. There have been reviews of commercial solutions of DA, particularly in the legal domain, but to date there has been no comprehensive review of the academic research on DA architectures and technologies. The current survey of DA reviews the academic literature and provides a clearer definition and characterization of DA and its features, identifies state-of-the-art DA architectures and technologies in academic research, and provides ideas that can lead to new research opportunities within the DA field in light of recent advances in generative AI and large language models.

Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-spoofing, complementary information presented in multi-order spectral patterns have not been well explored, which limits their effectiveness for varying spoofing attacks. Therefore, we propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. Specifically, spectral patterns up to second-order are fused in a coarse-to-fine manner and two branches are designed for the fine-level fusion from the spectral and temporal contexts. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset: ASVspoof2019 LA Challenge.

A fundamental challenge in the current NLP context, dominated by language models, comes from the inflexibility of current architectures to 'learn' new information. While model-centric solutions like continual learning or parameter-efficient fine tuning are available, the question still remains of how to reliably identify changes in language or in the world. In this paper, we propose WikiTiDe, a dataset derived from pairs of timestamped definitions extracted from Wikipedia. We argue that such resource can be helpful for accelerating diachronic NLP, specifically, for training models able to scan knowledge resources for core updates concerning a concept, an event, or a named entity. Our proposed end-to-end method is fully automatic, and leverages a bootstrapping algorithm for gradually creating a high-quality dataset. Our results suggest that bootstrapping the seed version of WikiTiDe leads to better fine-tuned models. We also leverage fine-tuned models in a number of downstream tasks, showing promising results with respect to competitive baselines.

Multimodal Entity Linking (MEL) is the task of mapping mentions with multimodal contexts to the referent entities from a knowledge base (e.g. Wikipedia). Existing MEL methods mainly focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters, which can be prohibitively costly and difficult to scale in the era of Large Language Models (LLMs). In this work, we propose GEMEL, a simple yet effective Generative Multimodal Entity Linking framework based on LLMs, which directly generates target entity names. We keep the vision and language model frozen and only train a feature mapper to enable cross-modality interactions. To adapt LLMs to the MEL task, we take advantage of the emergent in-context learning capability of LLMs by retrieving multimodal instances as demonstrations. Extensive experiments show that, with only ~0.3% of the model parameters fine-tuned, GEMEL achieves state-of-the-art results on two well-established MEL datasets (7.7% accuracy gains on WikiDiverse and 8.8% accuracy gains on WikiMEL). The performance gain stems from mitigating the popularity bias of LLM predictions and disambiguating less common entities effectively. Further analysis verifies the generality and scalability of GEMEL. Our approach is compatible with any off-the-shelf language model, paving the way towards an efficient and general solution for utilizing LLMs in the MEL task.

The explosion of content generated by Artificial Intelligence models has initiated a cultural shift in arts, music, and media, where roles are changing, values are shifting, and conventions are challenged. The readily available, vast dataset of the internet has created an environment for AI models to be trained on any content on the web. With AI models shared openly, and used by many, globally, how does this new paradigm shift challenge the status quo in artistic practices? What kind of changes will AI technology bring into music, arts, and new media?

The field of multimodal research focusing on the comprehension and creation of both images and text has witnessed significant strides. This progress is exemplified by the emergence of sophisticated models dedicated to image captioning at scale, such as the notable Flamingo model and text-to-image generative models, with DALL-E serving as a prominent example. An interesting question worth exploring in this domain is whether Flamingo and DALL-E understand each other. To study this question, we propose a reconstruction task where Flamingo generates a description for a given image and DALL-E uses this description as input to synthesize a new image. We argue that these models understand each other if the generated image is similar to the given image. Specifically, we study the relationship between the quality of the image reconstruction and that of the text generation. We find that an optimal description of an image is one that gives rise to a generated image similar to the original one. The finding motivates us to propose a unified framework to finetune the text-to-image and image-to-text models. Concretely, the reconstruction part forms a regularization loss to guide the tuning of the models. Extensive experiments on multiple datasets with different image captioning and image generation models validate our findings and demonstrate the effectiveness of our proposed unified framework. As DALL-E and Flamingo are not publicly available, we use Stable Diffusion and BLIP in the remaining work. Project website: https://dalleflamingo.github.io.

A half-formed thought feels worse than an empty head--the tip-of-the-tongue sensation, the inkling of a there there without the foggiest notion of how to get, well, there. Especially dire is when the "what" that we wish to articulate feels half-formed itself, something observable yet emergent, for which the masses have yet to find language. But all we have is language, of course, and so we must muddle through, reaching for a word to serve as a placeholder for our idea until something better comes along. Some would say that finding new language is the work of scholars, but in the age of the Internet we may have lost track of who is leading whom. However provisional, the placeholders sometimes stick.

Amazon's virtual assistant Alexa has been accused of sexism after being unable to respond to a question about the Lionesses' World Cup semi-final. British academic Dr Joanne Rodda asked Alexa for the result of Wednesday's match against Australia, which England won 3-1. But the supposedly'smart' technology didn't even know the match had taken place as it was only familiar with the men's game, the BBC reports. Astonishingly, when Dr Rodda asked'for the result of the England-Australia football match', Alexa said there was no such match. Amazon admitted the mistake was due to an'error' – although it didn't specify the cause – and that Alexa will get better at learning over time.

Loco-manipulation planning skills are pivotal for expanding the utility of robots in everyday environments. These skills can be assessed based on a system's ability to coordinate complex holistic movements and multiple contact interactions when solving different tasks. However, existing approaches have been merely able to shape such behaviors with hand-crafted state machines, densely engineered rewards, or pre-recorded expert demonstrations. Here, we propose a minimally-guided framework that automatically discovers whole-body trajectories jointly with contact schedules for solving general loco-manipulation tasks in pre-modeled environments. The key insight is that multi-modal problems of this nature can be formulated and treated within the context of integrated Task and Motion Planning (TAMP). An effective bilevel search strategy is achieved by incorporating domain-specific rules and adequately combining the strengths of different planning techniques: trajectory optimization and informed graph search coupled with sampling-based planning. We showcase emergent behaviors for a quadrupedal mobile manipulator exploiting both prehensile and non-prehensile interactions to perform real-world tasks such as opening/closing heavy dishwashers and traversing spring-loaded doors. These behaviors are also deployed on the real system using a two-layer whole-body tracking controller.