4 papers · 1 filter
xHC: Expanded Hyper-Connections
Xiangdong Zhang, Xiaohan Qin, Sunan Zou +10
Hyper-Connections (HC) expand the residual stream of Transformers into parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained H…
JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation
Yebin Yang, Huaijin Wu, Fu Guo +5
LLMs have traditionally scaled along dense dimensions, where performance is coupled with near-linear increases in computational cost. While MoE decouples capacity from compute, it…
NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
Xiaohan Qin, Xiaoxing Wang, Ning Liao +1
Multi-Task Learning (MTL) enables a single model to learn multiple tasks simultaneously, leveraging knowledge transfer among tasks for enhanced generalization, and has been widely…
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
Ning Liao, Xiaoxing Wang, Zehao Lin +18
A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM u…