Related papers: KID: Knowledge-Injected Dual-Head Learning for Kno…

Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series data analysis. These models capture complex, sequential patterns in time series,…

Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in decentralized or secure AI ecosystems, privacy regulations and proprietary interests often…

Knowledge editing enables multimodal large language models (MLLMs) to efficiently update outdated or incorrect information. However, existing benchmarks primarily emphasize cognitive-level modifications while lacking a focus on deeper…

Recently, deep supervised cross-modal hashing methods have achieve compelling success by learning semantic information in a self-supervised way. However, they still suffer from the key limitation that the multi-label semantic extraction…

Social media platforms enable the propagation of hateful content across different modalities such as textual, auditory, and visual, necessitating effective detection methods. While recent approaches have shown promise in handling individual…

Hate speech detection in Devanagari-scripted social media memes presents compounded challenges: multimodal content structure, script-specific linguistic complexity, and extreme data scarcity in low-resource settings. This paper presents our…

Large-scale short-video search ranking models are typically trained on sparse co-occurrence signals over hashed item identifiers (HIDs). While effective at memorizing frequent interactions, such ID-based models struggle to generalize to…

Early detection of mental health conditions, particularly stress and depression, from social media text remains a challenging open problem in computational psychiatry and natural language processing. Automated systems must contend with…

Warning: This paper contains memes that may be offensive to some readers. Multimodal Internet Memes are now a ubiquitous fixture in online discourse. One strand of meme-based research is the classification of memes according to various…

In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this challenge, we propose a novel approach called Meta-learned…

Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual…

Knowledge editing has emerged as an efficient technique for updating the knowledge of large language models (LLMs), attracting increasing attention in recent years. However, there is a lack of effective measures to prevent the malicious…

Large language models are now embedded in everyday writing workflows, making reliable AI-generated text detection important for academic integrity, content moderation, and provenance tracking. In practice, however, a detector must do more…

Language models have the potential to assess mental health using social media data. By analyzing online posts and conversations, these models can detect patterns indicating mental health conditions like depression, anxiety, or suicidal…

Recently, multimodal large language models (MLLMs) have been widely applied to reasoning tasks. However, they suffer from limited multi-rationale semantic modeling, insufficient logical robustness, and are susceptible to misleading…

Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with…

With massive data being generated daily and the ever-increasing interconnectivity of the world's Internet infrastructures, a machine learning based intrusion detection system (IDS) has become a vital component to protect our economic and…

Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention. Although high-dimensional KGE methods offer better performance, they come at the expense of…

Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph.Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering…

Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. To reduce the domain discrepancy, existing methods mainly attempt to generate pseudo labels…