Related papers: LLM-AD: Large Language Model based Audio Descripti…
Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that…
Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, traditional animation workflows present significant usability…
Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty.…
Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of…
The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard decoding methods often fail to robustly satisfy these…
Large language models have enabled automated algorithm design (AAD) by generating optimization algorithms directly from natural-language prompts. While evolutionary frameworks such as LLaMEA demonstrate strong exploratory capabilities…
Storytelling aims to generate reasonable and vivid narratives based on an ordered image stream. The fidelity to the image story theme and the divergence of story plots attract readers to keep reading. Previous works iteratively improved the…
The adaptation of Large-Scale Language Models (LLMs) to specific domains depends on high-quality fine-tuning datasets, particularly in instructional format (e.g., Question-Answer - Q&A). However, generating these datasets, particularly from…
Autonomous driving systems (ADS) are safety-critical and require comprehensive testing before their deployment on public roads. While existing testing approaches primarily aim at the criticality of scenarios, they often overlook the…
In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite…
We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to be aligned both globally and temporally with the input audio:…
Large Multimodal Models (LMMs) have demonstrated exceptional performance in video captioning tasks, particularly for short videos. However, as the length of the video increases, generating long, detailed captions becomes a significant…
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images,…
The latest advancements in AI and deep learning have led to a breakthrough in large language model (LLM)-based agents such as GPT-4. However, many commercial conversational agent development tools are pipeline-based and have limitations in…
Creators struggle to edit long-form, narrative-rich videos not because of UI complexity, but due to the cognitive demands of searching, storyboarding, and sequencing hours of footage. Existing transcript- or embedding-based methods fall…
Autonomous driving (AD) has made significant strides in recent years. However, existing frameworks struggle to interpret and execute spontaneous user instructions, such as "overtake the car ahead." Large Language Models (LLMs) have…
Developing autonomous driving systems (ADSs) involves generating and storing extensive log data from test drives, which is essential for verification, research, and simulation. However, these high-frequency logs, recorded over varying…
Large language models (LLMs) have advanced in text and vision, but their reasoning on audio remains limited. Most existing methods rely on dense audio embeddings, which are difficult to interpret and often fail on structured reasoning…
Video databases from the internet are a valuable source of text-audio retrieval datasets. However, given that sound and vision streams represent different "views" of the data, treating visual descriptions as audio descriptions is far from…
LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only…