-
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 326 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 449 -
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Paper • 2512.02556 • Published • 267
fangweichao
samchao
·
AI & ML interests
PCTR, MULTI TASK LEARNING
Organizations
GO-GRASHMAN
-
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 326 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 449 -
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Paper • 2512.02556 • Published • 267
models 0
None public yet
datasets 0
None public yet