This work presents a seminal approach for synthesizing images from WiFi Channel State Information (CSI) in through-wall scenarios. Leveraging the strengths of WiFi, such as cost-effectiveness, illumination invariance, and wall-penetrating capabilities, our approach enables visual monitoring of indoor environments beyond room boundaries and without the need for cameras. More generally, it improves the interpretability of WiFi CSI by unlocking the option to perform image-based downstream tasks, e.g., visual activity recognition. In order to achieve this crossmodal translation from WiFi CSI to images, we rely on a multimodal Variational Autoencoder (VAE) adapted to our problem specifics. We extensively evaluate our proposed methodology through an ablation study on architecture configuration and a quantitative/qualitative assessment of reconstructed images. Our results demonstrate the viability of our method and highlight its potential for practical applications.
We propose a framework to learn semantics from raw audio signals using two types of representations, encoding contextual and phonetic information respectively. Specifically, we introduce a speech-to-unit processing pipeline that captures two types of representations with different time resolutions. For the language model, we adopt a dual-channel architecture to incorporate both types of representation. We also present new training objectives, masked context reconstruction and masked context prediction, that push models to learn semantics effectively. Experiments on the sSIMI metric of Zero Resource Speech Benchmark 2021 and Fluent Speech Command dataset show our framework learns semantics better than models trained with only one type of representation.
In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA dataset). Current approaches resort supplement 3D reasoning with 2D information. However, these methods face challenges: either they use top-down 2D views that introduce overly complex and sometimes question-irrelevant visual clues, or they rely on globally aggregated scene/image-level representations from 2D VLMs, losing the fine-grained vision-language correlations. To overcome these limitations, our approach utilizes question-conditional 2D view selection procedure, pinpointing semantically relevant 2D inputs for crucial visual clues. We then integrate this 2D knowledge into the 3D-VQA system via a two-branch Transformer structure. This structure, featuring a Twin-Transformer design, compactly combines 2D and 3D modalities and captures fine-grained correlations between modalities, allowing them mutually augmenting each other. Integrating proposed mechanisms above, we present BridgeQA, that offers a fresh perspective on multi-modal transformer-based architectures for 3D-VQA. Experiments validate that BridgeQA achieves state-of-the-art on 3D-VQA datasets and significantly outperforms existing solutions. Code is available at $\href{https://github.com/matthewdm0816/BridgeQA}{\text{this URL}}$.
Current visual question answering (VQA) models tend to be trained and evaluated on image-question pairs in isolation. However, the questions people ask are dependent on their informational needs and prior knowledge about the image content. To evaluate how situating images within naturalistic contexts shapes visual questions, we introduce CommVQA, a VQA dataset consisting of images, image descriptions, real-world communicative scenarios where the image might appear (e.g., a travel website), and follow-up questions and answers conditioned on the scenario. We show that CommVQA poses a challenge for current models. Providing contextual information to VQA models improves performance broadly, highlighting the relevance of situating systems within a communicative scenario.
We present Polish Information Retrieval Benchmark (PIRB), a comprehensive evaluation framework encompassing 41 text information retrieval tasks for Polish. The benchmark incorporates existing datasets as well as 10 new, previously unpublished datasets covering diverse topics such as medicine, law, business, physics, and linguistics. We conduct an extensive evaluation of over 20 dense and sparse retrieval models, including the baseline models trained by us as well as other available Polish and multilingual methods. Finally, we introduce a three-step process for training highly effective language-specific retrievers, consisting of knowledge distillation, supervised fine-tuning, and building sparse-dense hybrid retrievers using a lightweight rescoring model. In order to validate our approach, we train new text encoders for Polish and compare their results with previously evaluated methods. Our dense models outperform the best solutions available to date, and the use of hybrid methods further improves their performance.
Deep neural networks have made great achievements in rainfall prediction.However, the current forecasting methods have certain limitations, such as with blurry generated images and incorrect spatial positions. To overcome these challenges, we propose a Two-stage Rainfall-Forecasting Diffusion Model (TRDM) aimed at improving the accuracy of long-term rainfall forecasts and addressing the imbalance in performance between temporal and spatial modeling. TRDM is a two-stage method for rainfall prediction tasks. The task of the first stage is to capture robust temporal information while preserving spatial information under low-resolution conditions. The task of the second stage is to reconstruct the low-resolution images generated in the first stage into high-resolution images. We demonstrate state-of-the-art results on the MRMS and Swedish radar datasets. Our project is open source and available on GitHub at: \href{https://github.com/clearlyzerolxd/TRDM}{https://github.com/clearlyzerolxd/TRDM}.
While there is no replacement for the learned expertise, devotion, and social benefits of a guide dog, there are cases in which a robot navigation assistant could be helpful for individuals with blindness or low vision (BLV). This study investigated the potential for an industrial agile robot to perform guided navigation tasks. We developed two interface prototypes that allowed for spatial information between a human-robot pair: a voice-based app and a flexible, responsive handle. The participants (n=21) completed simple navigation tasks and a post-study survey about the prototype functionality and their trust in the robot. All participants successfully completed the navigation tasks and demonstrated the interface prototypes were able to pass spatial information between the human and the robot. Future work will include expanding the voice-based app to allow the robot to communicate obstacles to the handler and adding haptic signals to the handle design.
How information was acquired may become irrelevant. An obvious case is when something is confirmed many times. In terms of iterated belief revision, a specific revision may become irrelevant in presence of others. Simple repetitions are an example, but not the only case when this happens. Sometimes, a revision becomes redundant even in presence of none equal, or even no else implying it. A necessary and sufficient condition for the redundancy of the first of a sequence of lexicographic revisions is given. The problem is coNP-complete even with two propositional revisions only. Complexity is the same in the Horn case but only with an unbounded number of revisions: it becomes polynomial with two revisions. Lexicographic revisions are not only relevant by themselves, but also because sequences of them are the most compact of the common mechanisms used to represent the state of an iterated revision process. Shortening sequences of lexicographic revisions is shortening the most compact representations of iterated belief revision states.
Causal graph recovery is essential in the field of causal inference. Traditional methods are typically knowledge-based or statistical estimation-based, which are limited by data collection biases and individuals' knowledge about factors affecting the relations between variables of interests. The advance of large language models (LLMs) provides opportunities to address these problems. We propose a novel method that utilizes the extensive knowledge contained within a large corpus of scientific literature to deduce causal relationships in general causal graph recovery tasks. This method leverages Retrieval Augmented-Generation (RAG) based LLMs to systematically analyze and extract pertinent information from a comprehensive collection of research papers. Our method first retrieves relevant text chunks from the aggregated literature. Then, the LLM is tasked with identifying and labelling potential associations between factors. Finally, we give a method to aggregate the associational relationships to build a causal graph. We demonstrate our method is able to construct high quality causal graphs on the well-known SACHS dataset solely from literature.
Clustering is a pivotal challenge in unsupervised machine learning and is often investigated through the lens of mixture models. The optimal error rate for recovering cluster labels in Gaussian and sub-Gaussian mixture models involves ad hoc signal-to-noise ratios. Simple iterative algorithms, such as Lloyd's algorithm, attain this optimal error rate. In this paper, we first establish a universal lower bound for the error rate in clustering any mixture model, expressed through a Chernoff divergence, a more versatile measure of model information than signal-to-noise ratios. We then demonstrate that iterative algorithms attain this lower bound in mixture models with sub-exponential tails, notably emphasizing location-scale mixtures featuring Laplace-distributed errors. Additionally, for datasets better modelled by Poisson or Negative Binomial mixtures, we study mixture models whose distributions belong to an exponential family. In such mixtures, we establish that Bregman hard clustering, a variant of Lloyd's algorithm employing a Bregman divergence, is rate optimal.