HASTE introduces group-shared fixed fan-in sparsity for multi-label classification, achieving significant wall-clock speedups (up to 25x in backward pass) by enabling efficient GPU execution while mai…

The paper proposes a zero-shot multi-label topic classification framework and finds that while knowledge graph augmentation improves performance for smaller language models, it offers diminishing retu…

This paper compares multi-class and multi-label text classification models for assigning Common Weakness Enumeration (CWE) categories to Common Vulnerabilities and Exposures (CVE) records using three…

This paper compares specialized supervised Extreme Multi-Label Classification (XMLC) methods with lexical matching baselines and LLM-based methods for subject indexing contemporary German scientific l…

The paper formalizes the concept of calibration for probabilistic label ranking, demonstrating that popular models are often poorly calibrated and that calibration captures a meaningful quality dimens…

The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

The paper proposes WEINCE, a modified InfoNCE objective that uses extreme value theory corrections to improve contrastive learning by more accurately modeling the selection of hard negative examples.

EvoPool introduces an evolutionary multi-agent framework that efficiently generates high-quality, specialized supervision labels, significantly outperforming LLM annotation baselines across complex, l…

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

A hybrid active-online learning framework is proposed for label-efficient concept drift adaptation in optical network failure detection, achieving high accuracy and AUC scores with minimal samples and…

This paper proposes a lightweight encoder-based MEL solution called FAST-MEL that meets three objectives: high linking accuracy, computational efficiency, and storage efficiency.

This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

The paper proposes a zero-label malware family classification framework that uses a weighted hierarchical ensemble of large language models (LLMs) to classify malware without requiring labeled trainin…

This paper proposes an ensemble of two source separators, FTRNN and TF-Locoformer, trained with mixture invariant training (MixIT), and introduces mixture-constrained max pooling (MCM) to improve bird…

This paper proposes a method for quantizing large language models with cross-layer error compensation and finite-sample feature-statistics matching.

This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.