Related papers: Optimal Transport Regularization for Speech Text A…
Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine multiple task-specific models into a single multi-task model…
Large Audio Language Models (LALMs) have emerged as powerful tools for speech-related tasks but remain underexplored for fine-tuning, especially with limited speech data. To bridge this gap, we systematically examine how different…
Audio-Visual Speech Recognition (AVSR) seeks to model, and thereby exploit, the dynamic relationship between a human voice and the corresponding mouth movements. A recently proposed multimodal fusion strategy, AV Align, based on…
Speculative sampling reduces the latency of autoregressive decoding for target model LLMs without sacrificing inference quality, by using a cheap draft model to suggest a candidate token and a verification criterion to accept or resample…
Recent advancements in large language models (LLMs) have spurred interest in expanding their application beyond text-based tasks. A large number of studies have explored integrating other modalities with LLMs, notably speech modality, which…
Optimal transport (OT) aims to find a map $T$ that transports mass from one probability measure to another while minimizing a cost function. Recently, neural OT solvers have gained popularity in high dimensional biological applications such…
Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model…
With the growing influence of Large Language Models (LLMs), there is increasing interest in integrating speech representations with them to enable more seamless multi-modal processing and speech understanding. This study introduces a novel…
In this paper, we argue that viewing VICReg-a popular self-supervised learning (SSL) method--through the lens of spectral embedding reveals a potential source of sub-optimality: it may struggle to generalize robustly to unseen data due to…
Automatic Speech Recognition (ASR) has recently shown remarkable progress, but accurately transcribing children's speech remains a significant challenge. Recent developments in Large Language Models (LLMs) have shown promise in improving…
While Vision-Language Models (VLMs) enable high-level semantic reasoning for end-to-end autonomous driving, particularly in unstructured environments, existing off-road datasets suffer from language annotations that are weakly aligned with…
Traditional base station siting (BSS) methods rely heavily on drive testing and user feedback, which are laborious and require extensive expertise in communication, networking, and optimization. As large language models (LLMs) and their…
Open-vocabulary semantic segmentation (OVSS) entails assigning semantic labels to each pixel in an image using textual descriptions, typically leveraging world models such as CLIP. To enhance out-of-domain generalization, we propose Cost…
The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated…
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…
Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…
Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks. Recent advance in representation learning…
Large language models (LLMs) have recently been introduced to graph learning, aiming to extend their zero-shot generalization success to tasks where labeled graph data is scarce. Among these applications, inference over text-attributed…
Travel behavior prediction is a core problem in transportation demand management and is traditionally addressed using numerical models calibrated on observed data. With recent advances in large language models (LLMs), new opportunities have…
Large language models (LLMs) achieve strong capabilities by scaling model capacity and training data, yet many real-world deployments rely on smaller models trained or adapted from low-resource data. This gap motivates the need for…