6 papers · 1 filter
Auto-Adaptive PINNs with Applications to Phase Transitions
Kevin Buck, Woojeong Kim
We propose an adaptive sampling method for the training of Physics Informed Neural Networks (PINNs) which allows for sampling based on an arbitrary problem-specific heuristic which…
OverFill: Two-Stage Models for Efficient Language Model Decoding
Woojeong Kim, Junxiong Wang, Jing Nathan Yan +2
Large language models (LLMs) excel across diverse tasks but face significant deployment challenges due to high inference costs. LLM inference comprises prefill (compute-bound) and…
DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues
Kyochul Jang, Donghyeon Lee, Kyusik Kim +4
Existing function-calling benchmarks focus on single-turn interactions. However, they overlook the complexity of real-world scenarios. To quantify how existing benchmarks address p…
Approximating Language Model Training Data from Weights
John X. Morris, Junjie Oscar Yin, Woojeong Kim +2
Modern language models often have open weights but closed training data. We formalize the problem of data approximation from model weights and propose several baselines and metrics…
From Chat Logs to Collective Insights: Aggregative Question Answering
Wentao Zhang, Woojeong Kim, Yuntian Deng
Conversational agents powered by large language models (LLMs) are rapidly becoming integral to our daily interactions, generating unprecedented amounts of conversational data. Such…
A numerical scheme for a multi-scale model of thrombus in arteries
Woojeong Kim
In this article, the time-discretization of the fluid structure interaction model in the three-dimensional boundary domain is taken into account, which explains the mechanical inte…