Related papers: A Locally Executable AI System for Improving Preop…

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

Healthcare systems continuously generate vast amounts of electronic health records (EHRs), commonly stored in the Fast Healthcare Interoperability Resources (FHIR) standard. Despite the wealth of information in these records, their…

Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they…

The continued need for improvements in accuracy, throughput, and efficiency of Deep Neural Networks has resulted in a multitude of methods that make the most of custom architectures on FPGAs. These include the creation of hand-crafted…

We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory…

Despite recent advancements in domain adaptation techniques for large language models, these methods remain computationally intensive, and the resulting models can still exhibit hallucination issues. Most existing adaptation methods do not…

Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction. Recent advancements have showcased the potential of building intelligent spoken chatbots based on large language…

Large language models (LLMs) generate fluent and complex outputs but often fail to recognize their own mistakes and hallucinations. Existing approaches typically rely on external judges, multi-sample consistency, or text-based…

The development of large language models (LLMs) has successfully transformed knowledge-based systems such as open domain question nswering, which can automatically produce vast amounts of seemingly coherent information. Yet, those models…

Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficult because drones require low-latency closed-loop guidance under strict onboard compute…

The incessant advent of online services demands high speed and efficient recommender systems (ReS) that can maintain real-time performance along with processing very complex user-item interactions. The present study, therefore, considers…

In modern large language models (LLMs), handling very long context lengths presents significant challenges as it causes slower inference speeds and increased memory costs. Additionally, most existing pre-trained LLMs fail to generalize…

Cross-lingual adaptation has proven effective in spoken language understanding (SLU) systems with limited resources. Existing methods are frequently unsatisfactory for intent detection and slot filling, particularly for distant languages…

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

In this paper, we make the first attempt to understand and test potential computation efficiency robustness in state-of-the-art LLMs. By analyzing the working mechanism and implementation of 20,543 public-accessible LLMs, we observe a…

With the introduction of Transformers, different attention-based models have been proposed for image segmentation with promising results. Although self-attention allows capturing of long-range dependencies, it suffers from a quadratic…

In-Car Conversational Question Answering (ConvQA) systems significantly enhance user experience by enabling seamless voice interactions. However, assessing their accuracy and reliability remains a challenge. This paper explores the use of…

This study demonstrates that a Multimodal Large Language Model (MLLM) adapted via Low-Rank Adaptation (LoRA) can perform both Automatic Pronunciation Assessment (APA) and Mispronunciation Detection and Diagnosis (MDD) simultaneously.…

Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at kernel boundaries, utilizing only 21% of their peak memory…