Translating Expert Intuition into Quantifiable Features: Encode Investigator Domain Knowledge via LLM for Enhanced Predictive…
DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptationby Jie…
Quantifying the Capabilities of LLMs across Scale and Precisionby Sher Badshah, Hassan SajjadFirst submitted to…
TED: Accelerate Model Training by Internal Generalizationby Jinying Xiao, Ping Li, Jie NieFirst submitted to…
Parameter-Efficient Fine-Tuning with Discrete Fourier Transformby Ziqi Gao, Qichao Wang, Aochuan Chen, Zijing Liu, Bingzhe…
Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMsby Feiyang Kang,…
Text Quality-Based Pruning for Efficient Training of Language Modelsby Vasu Sharma, Karthik Padthe, Newsha Ardalani,…
HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language…
An empirical study of LLaMA3 quantization: from LLMs to MLLMsby Wei Huang, Xingyu Zheng, Xudong…
Bridging Vision and Language Spaces with Assignment Predictionby Jungin Park, Jiyoung Lee, Kwanghoon SohnFirst submitted…