While voice-based AI systems have achieved remarkable generative capabilities, their interactions often feel conversationally broken. This paper examines the in...
Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple...
Extracting coherent and human-understandable themes from large collections of unstructured historical newspaper archives presents significant challenges due to ...
Retrieval-augmented generation (RAG) models rely on retrieved evidence to guide large language model (LLM) generators, yet current systems treat retrieval as a ...
We consider the problem of auditing black-box large language models (LLMs) to ensure they behave reliably when deployed in production settings, particularly in ...
Social media serves as a critical medium in modern politics because it both reflects politicians' ideologies and facilitates communication with younger generati...
Reliable interpretation of multimodal data in dentistry is essential for automated oral healthcare, yet current multimodal large language models (MLLMs) struggl...
Key frame selection in video understanding presents significant challenges. Traditional top-K selection methods, which score frames independently, often fail to...
Large Language Models (LLMs) exhibit remarkable capabilities in natural language understanding and reasoning, but suffer from hallucination: the generation of f...
Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generat...
Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) ha...
Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities and safety, but it also ma...
