5 papers
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
Wanru Zhao, Yihong Chen, Yuzhi Tang +6
Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, det…
CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics
Wanru Zhao, Hongxiang Fan, Shell Xu Hu +3
Recent research has highlighted the importance of data quality in scaling large language models (LLMs). However, automated data quality control faces unique challenges in collabora…
Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance
Zhican Wang, Guanghui He, Lingjun Gao +6
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, combining high-quality reconstruction with efficient rendering. It has been widely adopte…
Cascadia: An Efficient Cascade Serving System for Large Language Models
Youhe Jiang, Fangcheng Fu, Wanru Zhao +4
Recent advances in large language models (LLMs) have intensified the need to deliver both rapid responses and high-quality outputs. More powerful models yield better results but in…
Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization
Hao Mark Chen, Zehuan Zhang, Wanru Zhao +2
Recent years have witnessed a significant increase in the adoption of AI techniques to enhance electronic design automation. In particular, the emergence of Large Language Models (…