Related papers: RADD: Retrieval-Augmented Discrete Diffusion for M…

Retrieval-Augmented Generation (RAG) has significantly mitigated the hallucinations of Large Language Models (LLMs) by grounding the generation with external knowledge. Recent extensions of RAG to graph-based retrieval offer a promising…

Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods…

In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors. We observe that off-the-shelf KD methods manifest their efficacy only when the teacher model and student counterpart share similar intermediate…

After natural disasters, accurate evaluations of damage to housing are important for insurance claims response and planning of resources. In this work, we introduce a novel multimodal retrieval-augmented generation (MM-RAG) framework. On…

Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems…

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework…

Retrieval-augmented generation (RAG) introduces additional information to enhance large language models (LLMs). In machine translation (MT), previous work typically retrieves in-context examples from paired MT corpora, or domain-specific…

Human multimodal emotion recognition (MER) seeks to infer human emotions by integrating information from language, visual, and acoustic modalities. Although existing MER approaches have achieved promising results, they still struggle with…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

Multimodal Knowledge Graph Completion (MMKGC) aims to address the critical issue of missing knowledge in multimodal knowledge graphs (MMKGs) for their better applications. However, both the previous MMGKC and negative sampling (NS)…

Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods do not take full advantage of the dark knowledge hidden in…

Knowledge distillation (KD) aims to transfer knowledge from a large-scale teacher model to a lightweight one, significantly reducing computational and storage requirements. However, the inherent learning capacity gap between the teacher and…

Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in quality due to…

Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model.…

Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG…

Existing multimodal Retrieval-Augmented Generation (RAG) methods for visually rich documents (VRD) are often biased towards retrieving salient knowledge(e.g., prominent text and visual elements), while largely neglecting the critical…

Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonly employ an embed-and-retrieve paradigm: learning user and…

Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features of the target itself and lead to…

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained…

Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowledge distillation (KD) is one of the widely used compression…