15 papers · 1 filter
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Dongfang Li, Xiaodong Luo, Ruoyu Sun +64
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pre…
Structured Episodic Event Memory
Zhengxuan Lu, Dongfang Li, Yukun Shi +3
Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails…
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
Zhuoen Chen, Dongfang Li, Meishan Zhang +2
Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation…
LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
Gang Lin, Dongfang Li, Zhuoen Chen +4
The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and laten…
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Xinping Zhao, Xinshuo Hu, Zifei Shan +14
Recent advancements in Large Language Models (LLMs)-based text embedding models primarily focus on data scaling or synthesis, yet limited exploration of training techniques and dat…
Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment
Zhenyu Liu, Dongfang Li, Xinshuo Hu +4
Recent studies have explored the working mechanisms of In-Context Learning (ICL). However, they mainly focus on classification and simple generation tasks, limiting their broader a…