Related papers: Multi-modal Knowledge Distillation-based Human Tra…

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation. Unlike previous anticipation tasks that aim at action label prediction, our work…

Multimedia online platforms (e.g., Amazon, TikTok) have greatly benefited from the incorporation of multimedia (e.g., visual, textual, and acoustic) content into their personal recommender systems. These modalities provide intuitive…

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions. In this paper, we present a Linear Distillation Learning, a simple remedy to improve the…

Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for real-world applications. In this regard, the knowledge…

The burgeoning complexity of contemporary deep learning models, while achieving unparalleled accuracy, has inadvertently introduced deployment challenges in resource-constrained environments. Knowledge distillation, a technique aiming to…

Large language models (LLMs) have recently demonstrated strong potential for autonomous vehicle motion planning by reformulating trajectory prediction as a language generation problem. However, deploying capable LLMs in resource-constrained…

Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher network to a small…

Multimodal recommendation exploits the rich multimodal information associated with users or items to enhance the representation learning for better performance. In these methods, end-to-end feature extractors (e.g., shallow/deep neural…

Recent recommender systems have started to employ knowledge distillation, which is a model compression technique distilling knowledge from a cumbersome model (teacher) to a compact model (student), to reduce inference latency while…

We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird's-Eye-View (BEV) segmentation. Our approach leverages a novel LiDAR image representation fused from range, intensity and…

Multi-modal recommendation systems, which integrate diverse types of information, have gained widespread attention in recent years. However, compared to traditional collaborative filtering-based multi-modal recommendation systems, research…

Attributes of sound inherent to objects can provide valuable cues to learn rich representations for object detection and tracking. Furthermore, the co-occurrence of audiovisual events in videos can be exploited to localize objects over the…

We propose ClassroomKD, a novel multi-mentor knowledge distillation framework inspired by classroom environments to enhance knowledge transfer between the student and multiple mentors with different knowledge levels. Unlike traditional…

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded…

Human capability to anticipate near future from visual observations and non-verbal cues is essential for developing intelligent systems that need to interact with people. Several research areas, such as human-robot interaction (HRI),…

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Motion forecasting has become an increasingly critical component of autonomous robotic systems. Onboard compute budgets typically limit the accuracy of real-time systems. In this work we propose methods of improving motion forecasting…

Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security…