Robots Have Been Seen and Not Heard: Effects of Consequential Sounds on Human-Perception of Robots

Many people expect robots to move fairly quietly, or make pleasant "beep boop" sounds or jingles similar to what they have observed in videos of robots. Unfortunately, this expectation of quietness does not match reality, as robots make machine sounds, known as 'consequential sounds', as they move and operate. As robots become more prevalent within society, understanding the sounds produced by robots and how these sounds are perceived by people is becoming increasingly important for positive human robot interactions (HRI). This paper investigates how people respond to the consequential sounds of robots, specifically how robots make a participant feel, how much they like the robot, would be distracted by the robot, and a person's desire to colocate with robots. Participants were shown 5 videos of different robots and asked their opinions on the robots and the sounds they made. This was compared with a control condition of completely silent videos. The results in this paper demonstrate with data from 182 participants (858 trials) that consequential sounds produced by robots have a significant negative effect on human perceptions of robots. Firstly there were increased negative 'associated affects' of the participants, such as making them feel more uncomfortable or agitated around the robot. Secondly, the presence of consequential sounds correlated with participants feeling more distracted and less able to focus. Thirdly participants reported being less likely to want to colocate in a shared environment with robots.

Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision

Cross-lingual question answering (CLQA) is a complex problem, comprising cross-lingual retrieval from a multilingual knowledge base, followed by answer generation either in English or the query language. Both steps are usually tackled by separate models, requiring substantial annotated datasets, and typically auxiliary resources, like machine translation systems to bridge between languages. In this paper, we show that CLQA can be addressed using a single encoder-decoder model. To effectively train this model, we propose a self-supervised method based on exploiting the cross-lingual link structure within Wikipedia. We demonstrate how linked Wikipedia pages can be used to synthesise supervisory signals for cross-lingual retrieval, through a form of cloze query, and generate more natural queries to supervise answer generation. Together, we show our approach, \texttt{CLASS}, outperforms comparable methods on both supervised and zero-shot language adaptation settings, including those using machine translation.

Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers

We present a novel bi-directional Transformer architecture (BiXT) which scales linearly with input size in terms of computational cost and memory consumption, but does not suffer the drop in performance or limitation to only one input modality seen with other efficient Transformer-based approaches. BiXT is inspired by the Perceiver architectures but replaces iterative attention with an efficient bi-directional cross-attention module in which input tokens and latent variables attend to each other simultaneously, leveraging a naturally emerging attention-symmetry between the two. This approach unlocks a key bottleneck experienced by Perceiver-like architectures and enables the processing and interpretation of both semantics (`what') and location (`where') to develop alongside each other over multiple layers -- allowing its direct application to dense and instance-based tasks alike. By combining efficiency with the generality and performance of a full Transformer architecture, BiXT can process longer sequences like point clouds or images at higher feature resolutions and achieves competitive performance across a range of tasks like point cloud part segmentation, semantic image segmentation and image classification.

Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering

While significant advancements have been made in video question answering (VideoQA), the potential benefits of enhancing model generalization through tailored difficulty scheduling have been largely overlooked in existing research. This paper seeks to bridge that gap by incorporating VideoQA into a curriculum learning (CL) framework that progressively trains models from simpler to more complex data. Recognizing that conventional self-paced CL methods rely on training loss for difficulty measurement, which might not accurately reflect the intricacies of video-question pairs, we introduce the concept of uncertainty-aware CL. Here, uncertainty serves as the guiding principle for dynamically adjusting the difficulty. Furthermore, we address the challenge posed by uncertainty by presenting a probabilistic modeling approach for VideoQA. Specifically, we conceptualize VideoQA as a stochastic computation graph, where the hidden representations are treated as stochastic variables. This yields two distinct types of uncertainty: one related to the inherent uncertainty in the data and another pertaining to the model's confidence. In practice, we seamlessly integrate the VideoQA model into our framework and conduct comprehensive experiments. The findings affirm that our approach not only achieves enhanced performance but also effectively quantifies uncertainty in the context of VideoQA.

Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval

Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are unwieldy, such as requiring explicit supervision, complex model architectures, or massive external models. We present $\texttt{ABEL}$, a simple but effective unsupervised method to enhance passage retrieval in zero-shot settings. Our technique follows a straightforward loop: a dense retriever learns from supervision signals provided by a reranker, and subsequently, the reranker is updated based on feedback from the improved retriever. By iterating this loop, the two components mutually enhance one another's performance. Experimental results demonstrate that our unsupervised $\texttt{ABEL}$ model outperforms both leading supervised and unsupervised retrievers on the BEIR benchmark. Meanwhile, it exhibits strong adaptation abilities to tasks and domains that were unseen during training. By either fine-tuning $\texttt{ABEL}$ on labelled data or integrating it with existing supervised dense retrievers, we achieve state-of-the-art results.\footnote{Source code is available at \url{https://github.com/Fantabulous-J/BootSwitch}.}

Noisy Self-Training with Synthetic Queries for Dense Retrieval

Although existing neural retrieval models reveal promising results when training data is abundant and the performance keeps improving as training data increases, collecting high-quality annotated data is prohibitively costly. To this end, we introduce a novel noisy self-training framework combined with synthetic queries, showing that neural retrievers can be improved in a self-evolution manner with no reliance on any external models. Experimental results show that our method improves consistently over existing methods on both general-domain (e.g., MS-MARCO) and out-of-domain (i.e., BEIR) retrieval benchmarks. Extra analysis on low-resource settings reveals that our method is data efficient and outperforms competitive baselines, with as little as 30% of labelled training data. Further extending the framework for reranker training demonstrates that the proposed method is general and yields additional gains on tasks of diverse domains.\footnote{Source code is available at \url{https://github.com/Fantabulous-J/Self-Training-DPR}}

Improving Denoising Diffusion Models via Simultaneous Estimation of Image and Noise

This paper introduces two key contributions aimed at improving the speed and quality of images generated through inverse diffusion processes. The first contribution involves reparameterizing the diffusion process in terms of the angle on a quarter-circular arc between the image and noise, specifically setting the conventional $\displaystyle \sqrt{\bar{\alpha}}=\cos(\eta)$. This reparameterization eliminates two singularities and allows for the expression of diffusion evolution as a well-behaved ordinary differential equation (ODE). In turn, this allows higher order ODE solvers such as Runge-Kutta methods to be used effectively. The second contribution is to directly estimate both the image ($\mathbf{x}_0$) and noise ($\mathbf{\epsilon}$) using our network, which enables more stable calculations of the update step in the inverse diffusion steps, as accurate estimation of both the image and noise are crucial at different stages of the process. Together with these changes, our model achieves faster generation, with the ability to converge on high-quality images more quickly, and higher quality of the generated images, as measured by metrics such as Frechet Inception Distance (FID), spatial Frechet Inception Distance (sFID), precision, and recall.

Hey That's Mine Imperceptible Watermarks are Preserved in Diffusion Generated Outputs

Generative models have seen an explosion in popularity with the release of huge generative Diffusion models like Midjourney and Stable Diffusion to the public. Because of this new ease of access, questions surrounding the automated collection of data and issues regarding content ownership have started to build. In this paper we present new work which aims to provide ways of protecting content when shared to the public. We show that a generative Diffusion model trained on data that has been imperceptibly watermarked will generate new images with these watermarks present. We further show that if a given watermark is correlated with a certain feature of the training data, the generated images will also have this correlation. Using statistical tests we show that we are able to determine whether a model has been trained on marked data, and what data was marked. As a result our system offers a solution to protect intellectual property when sharing content online.

Long-Term Prediction of Natural Video Sequences with Robust Video Predictors

Predicting high dimensional video sequences is a curiously difficult problem. The number of possible futures for a given video sequence grows exponentially over time due to uncertainty. This is especially evident when trying to predict complicated natural video scenes from a limited snapshot of the world. The inherent uncertainty accumulates the further into the future you predict making long-term prediction very difficult. In this work we introduce a number of improvements to existing work that aid in creating Robust Video Predictors (RoViPs). We show that with a combination of deep Perceptual and uncertainty-based reconstruction losses we are able to create high quality short-term predictions. Attention-based skip connections are utilised to allow for long range spatial movement of input features to further improve performance. Finally, we show that by simply making the predictor robust to its own prediction errors, it is possible to produce very long, realistic natural video sequences using an iterated single-step prediction task.

Motion Perceiver: Real-Time Occupancy Forecasting for Embedded Systems

This work introduces a flexible architecture for real-time occupancy forecasting. In contrast to existing, more computationally expensive architectures, the proposed model exploits recursive latent state estimation, using learned transformer-based prediction and update modules. This allows for highly efficient real-time inference on an embedded system (profiled on an Nvidia Xavier AGX), and the inclusion of a broad set of information from a diverse set of sensors. The architecture is able to process sparse and occluded observations of agent positions and scene context as this is made available, and does not require motion tracklet inputs. \networkName{} accomplishes this by encoding the scene into a latent state that evolves in time with self-attention and is updated with contextual information such as traffic signals, road topology or agent detections using cross-attention. Occupancy predictions are made by sparsely querying positions of interest as opposed to generating a fixed size raster image, which allows for variable resolution occupancy prediction or local querying by downstream trajectory optimisation algorithms, saving computational effort.