相关论文: Lyra: An Efficient and Speech-Centric Framework fo…

Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations. We define this phenomenon as cumulative contextual decay - a progressive degradation…

Multimodal large language models (MLLMs) have emerged as a promising paradigm for dental image analysis. However, their ability to capture the multi-level cognitive processes required for radiographic analysis remains unclear. Here, we…

Recent advancements in Multimodal Large Language Models (MLLMs) pursue omni-perception capabilities, yet integrating robust sensory grounding with complex reasoning remains a challenge, particularly for underrepresented regions. In this…

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

MLLMs have demonstrated remarkable comprehension and reasoning capabilities with complex language and visual data. These advances have spurred the vision of establishing a generalist robotic MLLM proficient in understanding complex human…

Recent multimodal foundation models are primarily trained on English or high resource European language data, which hinders their applicability to other medium and low-resource languages. To address this limitation, we introduce Chitrarth…

As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual…

Speech Large Language Models (LLMs) that understand and follow instructions in many languages are useful for real-world interaction, but are difficult to train with supervised fine-tuning, requiring large, task-specific speech corpora.…

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs,…

Silent Speech Interfaces (SSIs) offer a noninvasive alternative to brain-computer interfaces for soundless verbal communication. We introduce Multimodal Orofacial Neural Audio (MONA), a system that leverages cross-modal alignment through…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable effectiveness in various general-domain scenarios, such as visual question answering and image captioning. Recently, researchers have increasingly focused on empowering…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models (SpeechLMs). Earlier SpeechLMs focused on single-turn speech-based question answering (QA), where user…

Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse heterogeneous modalities, which incurs substantial data and compute costs and limits extensibility. We present Training-Free Large Language…

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

Single large language models (LLMs) often fall short when faced with the ever-growing range of tasks, making a single-model approach insufficient. We address this challenge by proposing ORI (O Routing Intelligence), a dynamic framework that…

Emotion recognition from speech is a challenging task that requires capturing both linguistic and paralinguistic cues, with critical applications in human-computer interaction and mental health monitoring. Recent works have highlighted the…

This paper investigates and validates the impact of fine-tuning on large language model performance, focusing on parameter-efficient methods (LoRA and QLoRA). We evaluate model capabilities across three key domains: (1) commonsense…

Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and compute-heavy. The tutorial offers an overview of this emerging research area for…

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker…