Real-world machine learning applications often involve data from multiple modalities that must be integrated effectively to make robust predictions. However, in many practical settings, not all modalities are available for every sample, and acquiring additional modalities can be costly. This raises the question: which samples should be prioritized for additional modality acquisition when resources are limited? While prior work has explored individual-level acquisition strategies and training-time active learning paradigms, test-time and cohort-based acquisition remain underexplored. We introduce Cohort-based Active Modality Acquisition (CAMA), a novel test-time setting to formalize the challenge of selecting which samples should receive additional modalities. We derive acquisition strategies that leverage a combination of generative imputation and discriminative modeling to estimate the expected benefit of acquiring missing modalities based on common evaluation metrics. We also introduce upper-bound heuristics that provide performance ceilings to benchmark acquisition strategies. Experiments on multimodal datasets with up to 15 modalities demonstrate that our proposed imputation-based strategies can more effectively guide the acquisition of additional modalities for selected samples compared with methods relying solely on unimodal information, entropy-based guidance, or random selection. We showcase the real-world relevance and scalability of our method by demonstrating its ability to effectively guide the costly acquisition of proteomics data for disease prediction in a large prospective cohort, the UK Biobank (UKBB). Our work provides an effective approach for optimizing modality acquisition at the cohort level, enabling more effective use of resources in constrained settings.

This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for identifying unsafe content and its categories, their generative architecture inherently lacks direct class-level probabilities, which hinders model confidence assessment and performance interpretation. This limitation complicates the setting of dynamic thresholds for content moderation and impedes fine-grained error analysis. This research proposes and evaluates three novel token-level probability estimation approaches to bridge this gap. The aim is to enhance model interpretability and accuracy, and evaluate the generalizability of this framework across different instruction-tuned models. Through extensive experimentation on a synthetically generated, rigorously annotated dataset, it is demonstrated that leveraging token logits significantly improves the interpretability and reliability of generative classifiers, enabling more nuanced content safety moderation.

Estimation of mutual information from observed samples is a basic primitive in machine learning, useful in several learning tasks including correlation mining, information bottleneck, Chow-Liu tree, and conditional independence testing in (causal) graphical models.

We analyze the information-theoretic limits for the recovery of node labels in several network models.

In Section 3.2, we proposed the cross-distillation (XD) learning scheme. ImageNet-1K The encoders (MobileNet, EfficientNet, ResNet-50) are trained on ImageNet-1K with 100/200/300 epochs from scratch with the proposed method. We set the batch to 256 with a learning rate = 0.8. We employ the LARS optimizer with weight decay set to 1.5e-6. The hidden layer dimension of the projector is 4096.

Contrastive learning (CL) has been widely investigated with various learning mechanisms and achieves strong capability in learning representations of data in a self-supervised manner using unlabeled data. A common fashion of contrastive learning on this line is employing large-sized encoders to achieve comparable performance as the supervised learning counterpart. Despite the success of the labelless training, current contrastive learning algorithms failed to achieve good performance with lightweight (compact) models, e.g., MobileNet, while the requirements of the heavy encoders impede the energy-efficient computation, especially for resource-constrained AI applications. Motivated by this, we propose a new self-supervised CL scheme, named SACL-XD, consisting of two technical components, S limmed A symmetrical C ontrastive L earning (SACL) and Cross - D istillation (XD), which collectively enable efficient CL with compact models.

All these tasks are benchmarks that are used for testing models with long-term memory. It is similar to the previous one. Each image is flattened to one dimensional vector. The agent can only move forward along the corridor. The agent receives the reward only at the end of the episode.

We analyze the information-theoretic limits for the recovery of node labels in several network models.

Lemma 4.2, we have that k x At test time, if we encounter this rare scenario of mapping to a bucket with no value learnt in it, we simply run an approximate nearest neighbor search among the train points. This leads to our stated sample complexity bound. Hence the total time taken would be O ( dk log( L/)) . The above theorem uses a lemma about Euclidean LSH, which we prove next. The total time required for a forward pass on a new test sample is O ( dk log(1 /)) .