6 papers
Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods
Xuefei Julie Wang, Hao Cui, Michael P. Brenner +1
Tree Search-based test-time scaling of LLMs is a powerful tool for automated scientific coding. However, pure Tree Search sometimes struggles with systematic exploration, becoming…
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
Xuefei Wang, Jun Han, Zixuan Wang +4
Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen conversational domains from only a handful of target-domain interactions. Existin…
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
Xuefei Wang, Jialu Wang, Fengbo Zhang +6
Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the under…
HiFloat4 Format for Language Model Pre-training on Ascend NPUs
Mehran Taghian, Yunke Peng, Xing Huang +22
Large foundation models have become central to modern machine learning, with performance scaling predictably with model size and data. However, training and deploying such models i…
An AI system to help scientists write expert-level empirical software
Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici +39
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. To address this, we…
WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction
Shuai Wang, Ke Zhang, Shaoxiong Lin +6
Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party pro…