Related papers: On Data Engineering for Scaling LLM Terminal Capab…

Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant,…

Vision-language models (VLMs) are highly effective but often underperform on specialized tasks; for example, Llava-1.5 struggles with chart and diagram understanding due to scarce task-specific training data. Existing training data, sourced…

Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to deploy and fine-tune LLMs on mobile edge devices with…

Despite recent progress, Biomedical Entity Linking (BEL) with large language models (LLMs) remains computationally inefficient and challenging to deploy in practical settings. In this work, we demonstrate that instruction-tuning of…

Large Language Models (LLMs) are increasingly used as autonomous agents for multi-step tasks. However, most existing frameworks fail to maintain a structured understanding of the task state, often relying on linear prompt concatenation or…

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

While large language models (LLMs) bring not only performance but also complexity, recent work has started to turn LLMs into data generators rather than task inferencers, where another affordable task model is trained for efficient…

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Generative AI like the Large Language Models (LLMs) has become more available for the general consumer in recent years. Publicly available services, e.g., ChatGPT, perform token generation on networked cloud server hardware, effectively…

The scaling of large language models (LLMs) is currently bottlenecked by the rigidity of distributed programming. While high-performance libraries like CuBLAS and NCCL provide optimized primitives, they lack the flexibility required for…

With the rapid advancement of semiconductor technology, Electronic Design Automation (EDA) has become an increasingly knowledge-intensive and document-driven engineering domain. Although large language models (LLMs) have shown strong…

Background and Objective: Biomedical Named Entity Recognition (BioNER) is a foundational task in medical informatics, crucial for downstream applications like drug discovery and clinical trial matching. However, adapting general-domain…

One of the key tasks in machine learning for tabular data is feature engineering. Although it is vital for improving the performance of models, it demands considerable human expertise and deep domain knowledge, making it labor-intensive…

Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution,…

Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning capacities, the resulting models are either closed-source…

Pretraining large language models effectively requires strategic data selection, blending and ordering. However, key details about data mixtures especially their scalability to longer token horizons and larger model sizes remain…

Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to expensive physical data acquisition, existing pipelines remain fragmented and…

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

Multimodal large language models (LLMs) empower LLMs to ingest inputs and generate outputs in multiple forms, such as text, image, and audio. However, the integration of multiple modalities introduces heterogeneity in both the model and…

In recent years, many techniques have been developed to improve the performance and efficiency of data center networks. While these techniques provide high accuracy, they are often designed using heuristics that leverage domain-specific…