Related papers: MAC: A Conversion Rate Prediction Benchmark Featur…

In recent years, data selection has emerged as a core issue for large-scale visual-language model pretraining, especially on noisy web-curated datasets. One widely adopted strategy assigns quality scores such as CLIP similarity for each…

The increasing availability and diversity of multimodal data in recommender systems offer new avenues for enhancing recommendation accuracy and user satisfaction. However, these systems must contend with high-dimensional, sparse user-item…

Multimodal representation learning seeks to create a unified representation space by integrating diverse data modalities to improve multimodal understanding. Traditional methods often depend on pairwise contrastive learning, which relies on…

A vastly growing literature on explaining deep learning models has emerged. This paper contributes to that literature by introducing a global gradient-based model-agnostic method, which we call Marginal Attribution by Conditioning on…

With the advancement of deep learning techniques, major cloud providers and niche machine learning service providers start to offer their cloud-based machine learning tools, also known as machine learning as a service (MLaaS), to the…

Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation,…

Multi-label image recognition is a fundamental task in computer vision. Recently, vision-language models have made notable advancements in this area. However, previous methods often failed to effectively leverage the rich knowledge within…

Automated machine learning (AutoML) has received increasing attention in the recent past. While the main tools for AutoML, such as Auto-WEKA, TPOT, and auto-sklearn, mainly deal with single-label classification and regression, there is very…

Multi-domain text classification (MDTC) aims to leverage all available resources from multiple domains to learn a predictive model that can generalize well on these domains. Recently, many MDTC methods adopt adversarial learning,…

The accurate prediction of material properties is crucial in a wide range of scientific and engineering disciplines. Machine learning (ML) has advanced the state of the art in this field, enabling scientists to discover novel materials and…

As we all know, multi-view data is more expressive than single-view data and multi-label annotation enjoys richer supervision information than single-label, which makes multi-view multi-label learning widely applicable for various pattern…

Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment. This paradigm is applicable to various industrial scenarios such as autonomous driving, quantitative trading, and…

Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three…

Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during…

In the pathway toward Artificial General Intelligence (AGI), understanding human's affection is essential to enhance machine's cognition abilities. For achieving more sensual human-AI interaction, Multimodal Affective Computing (MAC) in…

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

Open Set Recognition (OSR) has been an emerging topic. Besides recognizing predefined classes, the system needs to reject the unknowns. Prototype learning is a potential manner to handle the problem, as its ability to improve intra-class…

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually requires. This…

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal…