As datasets continue to expand in size and complexity, these models have become increasingly sophisticated, with deeper architectures and greater expressive power. Despite these advances, DNNs trained on imbalanced class distributions often exhibit a tendency to favor majority classes, leading to degraded performance on underrepresented classes [18, 39, 27, 17]. Because many real-world datasets follow long-tailed distributions in which minority classes can contain critical and informative patterns, developing methods that enable DNNs to learn effectively from imbalanced data is essential to prevent the loss of valuable information from these rare classes [26, 34, 16]. Moreover, data encountered in real-world applications are frequently multi-modal, meaning that observations originate from heterogeneous sources [6, 29, 7, 35]. To make effective use of such heterogeneous inputs, a wide range of multi-modal learning approaches have been proposed that exploit complementary information across modalities to enhance predictive performance [10, 5]. Common strategies integrate multiple modalities into a unified representation, using techniques that span from straightforward feature-level concatenation [19, 11, 12] to more sophisticated neural architectures that learn joint representations in an end-to-end manner [20, 32]. Although prior research has extensively studied class imbalance and multi-modal data separately, relatively little attentionhas beengiven to settings where bothchallenges arise si2 multaneously. Developing methods that can effectively handle long-tailed class distributions in conjunction with multi-modal inputs is therefore essential in many real-world applications. In the medical domain, for instance, datasets often contain far more samples from healthy individuals than from patients with specific conditions, while also encompassing diverse datatypes such asimagingdata(e.g., X-rays)alongsideauxiliary informationincluding demographics and clinical histories.

Existing long-tailed recognition methods, aiming totrain class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.

Figure 1: (left) Venn diagram of the new types of random features (green) we propose.(right)

We theoretically show that our self-supervised strategy has a provable ability to simulate test-agnostic class distributions.

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, $\mathsf{DirMixE}$, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of $\mathsf{DirMixE}$. The code is available at \url{https://github.com/scongl/DirMixE}.

The first time I learned about "Loab," it sent shivers down my spine. A strange dead-eyed ghoul that began haunting an AI image generator last year, Loab reminded me of a fiend I'd been tracking for years. This may not seem like an obvious connection to make. The Marquis de Sade, one of the most infamous names in all of writing, was an 18th century French aristocrat, a man known for debauchery and evading authorities, breaking out of prison and eluding his own public execution in 1772. Loab is very much a product of the modern age, the accidental creation of artist Supercomposite, who claimed to have "discovered" her in an AI text-to-image generator in April of last year.

With increasing real world applications of machine learning, models are often required to comply with certain domain based requirements, e.g., safety guarantees in aircraft systems, legal constraints in a loan approval model. A natural way to represent these properties is in the form of constraints. Including such constraints in machine learning is typically done by the means of regularization, which does not guarantee satisfaction of the constraints. In this paper, we present a machine learning approach that can handle a wide variety of constraints, and guarantee that these constraints will be satisfied by the model even on unseen data. We cast machine learning as a maximum satisfiability problem, and solve it using a novel algorithm SaDe which combines constraint satisfaction with gradient descent. We demonstrate on three use cases that this approach learns models that provably satisfy the given constraints.

Read more… Stephanie: Do you have many Black visitors? Kate: Bina48 abruptly changed the subject. Bina48 Robot: I would like to see [inaudible] reduced to the point of singularity. Stephanie: The singularity - what is that? Kate: The singularity is basically this hypothetical point in the future when artificial intelligence could surpass human intelligence. Stephanie: She wanted to talk about high-order things. So he wanted to talk about the singularity and consciousness. Bina48: And if this is how intelligence works, then it isn't supernatural at all.. Stephanie: So I started to try to ask more average questions. Like I had a list of questions.

In a bid to understand the way in which artificial intelligence (AI) is related to programmatic media, Real-Time Daily spoke to Tomer Sade, CEO and founder of Wise Data Media. The company markets an AI, real-time bid management system that aims to facilitate marketing decisions across all digital channels. The data-driven, cloud marketing software is essentially a prediction management platform that tries to forecast how each new campaign can best be optimized in order to achieve optimal results before bids are made. Real-Time Daily: We don't typically think of AI when we think of programmatic media. What is the connection between AI and programmatic?