Related papers: Multi-Sentence Grounding for Long-term Instruction…

Despite the strong reasoning capabilities of large language models (LLMs), optimizing the execution efficiency of tensor programs remains challenging due to the need for precise, composable transformation decisions. Recent LLM-guided…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

The temporal sentence grounding in video (TSGV) task is to locate a temporal moment from an untrimmed video, to match a language query, i.e., a sentence. Without considering bias in moment annotations (e.g., start and end positions in a…

In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and…

Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploying these methods to improve production ASR systems that are…

Large Language Model (LLM)-based Text-to-Speech (TTS) models have already reached a high degree of naturalness. However, the precision control of TTS inference is still challenging. Although instruction-based Text-to-Speech (Instruct-TTS)…

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…

A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate…

Dense video captioning is a challenging video understanding task which aims to simultaneously segment the video into a sequence of meaningful consecutive events and to generate detailed captions to accurately describe each event. Existing…

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…

While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative frames from videos remains a critical challenge. Existing…

In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems. Different from previous LLM-based ASR error correction methods, we propose a novel multi-stage…

Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtasks: Moment Retrieval (MR) and Highlight Detection (HD).…

Diffusion models have achieved remarkable progress in the field of video generation. However, their iterative denoising nature requires a large number of inference steps to generate a video, which is slow and computationally expensive. In…

Mathematical reasoning is regarded as a necessary ability for Language Models (LMs). Recent works demonstrate large LMs' impressive performance in solving math problems. The success is attributed to their Chain-of-Thought (CoT) reasoning…

Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while…

This submission investigates alternative machine learning models for predicting the HTER score on the sentence level. Instead of directly predicting the HTER score, we suggest a model that jointly predicts the amount of the 4 distinct…

We are committed to learning human skill generators at key-step levels. The generation of skills is a challenging endeavor, but its successful implementation could greatly facilitate human skill learning and provide more experience for…

Real-world video creation often involves a complex reasoning workflow of selecting relevant shots from noisy materials, planning missing shots for narrative completeness, and organizing them into coherent storylines. However, existing…

Representing text into a multidimensional space can be done with sentence embedding models such as Sentence-BERT (SBERT). However, training these models when the data has a complex multilevel structure requires individually trained…