Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of proposals that process audio-visual data and can be observed in the number of proposals in the past years. Thus encouraging the development of a comprehensive survey. Besides analyzing the models used in this context, we also discuss some tasks of definition and paradigm applied in AI multimedia. In addition, we investigate objective functions frequently used and discuss how audio-visual data is exploited in the optimization process, i.e., the different methodologies for representing knowledge in the audio-visual domain. In fact, we focus on how human-understandable mechanisms, i.e., structured knowledge that reflects comprehensible knowledge, can guide the learning process. Most importantly, we provide a summarization of the recent progress of Audio-Visual Correlation Learning (AVCL) and discuss the future research directions.

Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Although substantial progress has been made in time series forecasting, most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices (e.g., sensors, wearables) to a central cloud server. However, this paradigm has overloaded communication networks and raised privacy concerns. Federated learning, a popular privacy-preserving technique, enables collaborative model training across distributed data sources. However, directly applying federated learning to time series forecasting often yields suboptimal results, as time series data generated by different devices are inherently heterogeneous. In this paper, we propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers. Specifically, Fed-TREND generates two types of synthetic data. The first type of synthetic data captures the representative distribution information from clients' uploaded model updates and enhances clients' local training consensus. The second kind of synthetic data extracts long-term influence insights from global model update trajectories and is used to refine the global model after aggregation. Fed-TREND is compatible with most time series forecasting models and can be seamlessly integrated into existing federated learning frameworks to improve prediction performance. Extensive experiments on eight datasets, using several federated learning baselines and four popular time series forecasting models, demonstrate the effectiveness and generalizability of Fed-TREND.

Robots have the potential to enhance teaching of advanced computer science topics, making abstract concepts more tangible and interactive. In this paper, we present Timmy-a GoPiGo robot augmented with projections to demonstrate shortest path algorithms in an interactive learning environment. We integrated a JavaScript-based application that is projected around the robot, which allows users to construct graphs and visualise three different shortest path algorithms with colour-coded edges and vertices. Animated graph exploration and traversal are augmented by robot movements. To evaluate Timmy, we conducted two user studies. An initial study (= 10) to explore the feasibility of this type of teaching where participants were just observing both robot-synced and the on-screen-only visualisations. And a pilot study (= 6) where participants actively interacted with the system, constructed graphs and selected desired algorithms. In both studies we investigated the preferences towards the system and not the teaching outcome. Initial findings suggest that robots offer an engaging tool for teaching advanced algorithmic concepts, but highlight the need for further methodological refinements and larger-scale studies to fully evaluate their effectiveness.

When better to hold a conference on artificial intelligence and the countless ways it is advancing science than in those brief days between the first Nobel prizes being awarded in the field and the winners heading to Stockholm for the lavish white tie ceremony? It was fortuitous timing for Google DeepMind and the Royal Society who this week convened the AI for Science Forum in London. Last month, Google DeepMind bagged the Nobel prize in chemistry a day after AI took the physics prize. Scientists have worked with AI for years, but the latest generation of algorithms have brought us to brink of transformation, Demis Hassabis, the chief executive officer of Google DeepMind, told the meeting. "If we get it right, it should be an incredible new era of discovery and a new golden age, maybe even a kind of new renaissance," he said.

Joe Wolfel is the CEO and founder of Terradepth. He is passionate about helping people make better and faster decisions regarding what we do (and don't do) in the ocean. Terradepth designs and builds ocean-going robots at scale, deploys them, and delivers data through an ocean data platform tailored for the maritime community. Prior to Terradepth, Joe has helped start a couple other companies, worked as a management consultant, and served as a US Navy SEAL officer with deployments throughout the Middle East and Africa. Joe was educated at the US Naval Academy.

Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multimodal RLHF lies in its negative supervision, the logit of the rejected responses. We thus propose a novel negative supervised finetuning (nSFT) approach that fully excavates these information resided. Our nSFT disentangles this negative supervision in RLHF paradigm, and continually aligns VLMs with a simple SFT loss. This is more memory efficient than multimodal RLHF where 2 (e.g., DPO) or 4 (e.g., PPO) large VLMs are strictly required. The effectiveness of nSFT is rigorously proved by comparing it with various multimodal RLHF approaches, across different dataset sources, base VLMs and evaluation metrics. Besides, fruitful of ablations are provided to support our hypothesis. We hope this paper will stimulate further research to properly align large vision language models.

Referring Expression Comprehension (REC) aims to identify a particular object in a scene by a natural language expression, and is an important topic in visual language understanding. State-of-the-art methods for this task are based on deep learning, which generally requires expensive and manually labeled annotations. Some works tackle the problem with limited-supervision learning or relying on Large Vision and Language Models. However, the development of techniques to synthesize labeled data is overlooked. In this paper, we propose a novel framework that generates artificial data for the REC task, taking into account both textual and visual modalities. At first, our pipeline processes existing data to create variations in the annotations. Then, it generates an image using altered annotations as guidance. The result of this pipeline is a new dataset, called Harlequin, made by more than 1M queries. This approach eliminates manual data collection and annotation, enabling scalability and facilitating arbitrary complexity. We pre-train three REC models on Harlequin, then fine-tuned and evaluated on human-annotated datasets. Our experiments show that the pre-training on artificial data is beneficial for performance.

We consider the problem of learning an arbitrarily-biased ReLU activation (or neuron) over Gaussian marginals with the squared loss objective. Despite the ReLU neuron being the basic building block of modern neural networks, we still do not understand the basic algorithmic question of whether one arbitrary ReLU neuron is learnable in the non-realizable setting. In particular, all existing polynomial time algorithms only provide approximation guarantees for the better-behaved unbiased setting or restricted bias setting. Our main result is a polynomial time statistical query (SQ) algorithm that gives the first constant factor approximation for arbitrary bias. It outputs a ReLU activation that achieves a loss of $O(\mathrm{OPT}) + \varepsilon$ in time $\mathrm{poly}(d,1/\varepsilon)$, where $\mathrm{OPT}$ is the loss obtained by the optimal ReLU activation. Our algorithm presents an interesting departure from existing algorithms, which are all based on gradient descent and thus fall within the class of correlational statistical query (CSQ) algorithms. We complement our algorithmic result by showing that no polynomial time CSQ algorithm can achieve a constant factor approximation. Together, these results shed light on the intrinsic limitation of gradient descent, while identifying arguably the simplest setting (a single neuron) where there is a separation between SQ and CSQ algorithms.

We present an autoencoder-based semi-supervised approach to classify perceived human emotions from walking styles obtained from videos or motion-captured data and represented as sequences of 3D poses. Given the motion on each joint in the pose at each time step extracted from 3D pose sequences, we hierarchically pool these joint motions in a bottom-up manner in the encoder, following the kinematic chains in the human body. We also constrain the latent embeddings of the encoder to contain the space of psychologically-motivated affective features underlying the gaits. We train the decoder to reconstruct the motions per joint per time step in a top-down manner from the latent embeddings. For the annotated data, we also train a classifier to map the latent embeddings to emotion labels. Our semi-supervised approach achieves a mean average precision of 0.84 on the Emotion-Gait benchmark dataset, which contains both labeled and unlabeled gaits collected from multiple sources. We outperform current state-of-art algorithms for both emotion recognition and action recognition from 3D gaits by 7%--23% on the absolute. More importantly, we improve the average precision by 10%--50% on the absolute on classes that each makes up less than 25% of the labeled part of the Emotion-Gait benchmark dataset.

This paper introduces Open-Amp, a synthetic data framework for generating large-scale and diverse audio effects data. Audio effects are relevant to many musical audio processing and Music Information Retrieval (MIR) tasks, such as modelling of analog audio effects, automatic mixing, tone matching and transcription. Existing audio effects datasets are limited in scope, usually including relatively few audio effects processors and a limited amount of input audio signals. Our proposed framework overcomes these issues, by crowdsourcing neural network emulations of guitar amplifiers and effects, created by users of open-source audio effects emulation software. This allows users of Open-Amp complete control over the input signals to be processed by the effects models, as well as providing high-quality emulations of hundreds of devices. Open-Amp can render audio online during training, allowing great flexibility in data augmentation. Our experiments show that using Open-Amp to train a guitar effects encoder achieves new state-of-the-art results on multiple guitar effects classification tasks. Furthermore, we train a one-to-many guitar effects model using Open-Amp, and use it to emulate unseen analog effects via manipulation of its learned latent space, indicating transferability to analog guitar effects data.