4 papers
GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
Tianhao Chen, Xin Xu, Zijing Liu +12
Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretra…
Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
Xin Xu, Tianhao Chen, Fan Zhang +11
While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and re…
Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering
Awais Naeem, Tianhao Li, Huang-Ru Liao +9
Accurate diagnosis and prognosis assisted by pathology images are essential for cancer treatment selection and planning. Despite the recent trend of adopting deep-learning approach…
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning
Abhinav Bandari, Lu Yin, Cheng-Yu Hsieh +5
Network pruning has emerged as a potential solution to make LLMs cheaper to deploy. However, existing LLM pruning approaches universally rely on the C4 dataset as the calibration d…