Related papers: LARP: Language Audio Relational Pre-training for C…

Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing. Its employment ranges from sound event detection to text-to-audio generation. However, one of the main limitations is…

Contrastive language-audio pretraining (CLAP) is widely used for audio generation and recognition tasks. For example, CLAPScore, which utilizes the similarity of CLAP embeddings, has been a major metric for the evaluation of the relevance…

Capturing complex user preferences from sparse behavioral sequences remains a fundamental challenge in sequential recommendation. Recent latent reasoning methods have shown promise by extending test-time computation through multi-step…

Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories. To adapt CLAP to downstream tasks, prior works…

Webly supervised learning has attracted increasing attention for its effectiveness in exploring publicly accessible data at scale without manual annotation. However, most existing methods of learning with web datasets are faced with…

Continual learning aims to update a model so that it can sequentially learn new tasks without forgetting previously acquired knowledge. Recent continual learning approaches often leverage the vision-language model CLIP for its…

Compositional, structured models are appealing because they explicitly decompose problems and provide interpretable intermediate outputs that give confidence that the model is not simply latching onto data artifacts. Learning these models…

Many tasks in music information retrieval, such as recommendation, and playlist generation for online radio, fall naturally into the query-by-example setting, wherein a user queries the system by providing a song, and the system responds…

Recently, the usage of Contrastive Representation Learning (CRL) as a pre-training technique improves the performance of learning with noisy labels (LNL) methods. However, instead of pre-training, when trivially combining CRL loss with LNL…

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the…

Joint audio-text models are widely used for music retrieval, yet they struggle with semantic phenomena such as negation. Negation is fundamental for distinguishing the absence (or presence) of musical elements (e.g., "with vocals" vs.…

Class incremental learning refers to a special multi-class classification task, in which the number of classes is not fixed but is increasing with the continual arrival of new data. Existing researches mainly focused on solving catastrophic…

Continual fine-tuning of Large Language Models (LLMs) is hampered by the trade-off between efficiency and expressiveness. Low-Rank Adaptation (LoRA) offers efficiency but constrains the model's ability to learn new tasks and transfer…

Large Language Models (LLMs) have shown significant potential for improving recommendation systems through their inherent reasoning capabilities and extensive knowledge base. Yet, existing studies predominantly address warm-start scenarios…

Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop interactions largely…

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Traditional recommender systems primarily leverage identity-based (ID) representations for users and items, while the advent of pre-trained language models (PLMs) has introduced rich semantic modeling of item descriptions. However, PLMs…

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…

Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…