相关论文: FLUID: Flow-Latent Unified Integration via Token D…

Most existing federated learning algorithms are based on the vanilla FedAvg scheme. However, with the increase of data complexity and the number of model parameters, the amount of communication traffic and the number of iteration rounds for…

High-performance Radar-Camera 3D object detection can be achieved by leveraging knowledge distillation without using LiDAR at inference time. However, existing distillation methods typically transfer modality-specific features directly to…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without additional training. In current AV-LLMs, audio and video features are typically…

Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to…

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

Multi-modal object Re-IDentification (ReID) aims to obtain complete identity features across heterogeneous modalities. However, most existing methods rely on implicit feature fusion modules, making it difficult to model fine-grained…

Multimodal sentiment analysis, a pivotal task in affective computing, seeks to understand human emotions by integrating cues from language, audio, and visual signals. While many recent approaches leverage complex attention mechanisms and…

Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in…

Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scenes efficiently by dynamically scanning and…

Recent years have seen increasing employment of decision intelligence in electronic design automation (EDA), which aims to reduce the manual efforts and boost the design closure process in modern toolflows. However, existing approaches…

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation…

Cross-modal Knowledge Distillation has demonstrated promising performance on paired modalities with strong semantic connections, referred to as Symmetric Cross-modal Knowledge Distillation (SCKD). However, implementing SCKD becomes…

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Multimodal Emotion Recognition in Conversations (MERC) identifies emotional states across text, audio and video, which is essential for intelligent dialogue systems and opinion analysis. Existing methods emphasize heterogeneous modal fusion…

Scale variance is one of the crucial challenges in multi-scale object detection. Early approaches address this problem by exploiting the image and feature pyramid, which raises suboptimal results with computation burden and constrains from…

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various…

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervised knowledge distillation (SSKD) framework that compresses…