Related papers: Scaling Audio-Text Retrieval with Multimodal Large…

We propose a general feedback-driven retrieval-augmented generation (RAG) approach that leverages Large Audio Language Models (LALMs) to address the missing or imperfect synthesis of specific sound events in text-to-audio (TTA) generation.…

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, notably in connecting ideas and adhering to logical rules to solve problems. These models have evolved to accommodate various data modalities, including sound…

Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this…

Video-language pre-training is a typical and challenging problem that aims at learning visual and textual representations from large-scale data in a self-supervised way. Existing pre-training approaches either captured the correspondence of…

In this study, we introduce a novel cross-modal retrieval task involving speaker descriptions and their corresponding audio samples. Utilizing pre-trained speaker and text encoders, we present a simple learning framework based on…

This study demonstrates that a Multimodal Large Language Model (MLLM) adapted via Low-Rank Adaptation (LoRA) can perform both Automatic Pronunciation Assessment (APA) and Mispronunciation Detection and Diagnosis (MDD) simultaneously.…

Recent advancements in multi-modal large language models (MLLMs) have led to substantial improvements in visual understanding, primarily driven by sophisticated modality alignment strategies. However, predominant approaches prioritize…

State-of-the-art retrieval models typically address a straightforward search scenario, in which retrieval tasks are fixed (e.g., finding a passage to answer a specific question) and only a single modality is supported for both queries and…

Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding…

Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple…

Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples…

Reranking is a critical component in many information retrieval pipelines. Despite remarkable progress in text-only settings, multimodal reranking remains challenging, particularly when the candidate set contains hybrid text and image…

We present a joint Speech and Language Model (SLM), a multitask, multilingual, and dual-modal model that takes advantage of pretrained foundational speech and language models. SLM freezes the pretrained foundation models to maximally…

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous},…

Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features with textual context remains unclear. We adapt causal tracing to investigate the internal…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

Unified multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both multimodal understanding and generation capabilities,…

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion,…

Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition…

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…