3 papers
cs.CL2026
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
cs.LG2026
SelfAI: A self-directed framework for long-horizon scientific discovery
Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng +9
Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited ins…
cs.LG2025
FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning
Xiaobing Yu, Jin Yang, Xiao Wu +2
How to adapt a pre-trained model continuously for sequential tasks with different prediction class labels and domains and finally learn a generalizable model across diverse tasks i…