Klear team, Kuaishou Technology

company

https://github.com/Kwai-Klear

Activity Feed

AI & ML interests

LLM foundation&research @ Kuaishou Technology

Recent Activity

xiaoxuanzi updated a model 14 days ago

Kwai-Klear/GoLongRL-4B

xiaoxuanzi updated a model 14 days ago

Kwai-Klear/GoLongRL-30B-A3B

xiaoxuanzi updated a dataset 14 days ago

Kwai-Klear/GoLongRL

View all activity

Klear team, Kuaishou Technology

AI & ML interests

Recent Activity

Kwai-Klear 's collections 6

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Kwai-Klear/GoLongRL-30B-A3B

Kwai-Klear/GoLongRL-4B

Kwai-Klear/GoLongRL

Kwai-Klear/Klear-AgentForge-8B-SFT

Kwai-Klear/SWE-smith-mini_swe_agent_plus-trajectories-66k

Kwai-Klear/Klear-AgentForge-8B

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

Kwai-Klear/Klear-Reasoner-8B

Kwai-Klear/SWE-smith-mini_swe_agent_plus-trajectories-66k

Kwai-Klear/Klear-AgentForge-8B-SFT

Kwai-Klear/Klear-46B-A2.5B-Base

Kwai-Klear/Klear-46B-A2.5B-Instruct

Kwai-Klear/RLEP_dataset

RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning

Kwai-Klear/qwen2.5-math-rlep

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Kwai-Klear/GoLongRL-30B-A3B

Kwai-Klear/GoLongRL-4B

Kwai-Klear/GoLongRL

Kwai-Klear/SWE-smith-mini_swe_agent_plus-trajectories-66k

Kwai-Klear/Klear-AgentForge-8B-SFT

Kwai-Klear/Klear-AgentForge-8B-SFT

Kwai-Klear/SWE-smith-mini_swe_agent_plus-trajectories-66k

Kwai-Klear/Klear-AgentForge-8B

Kwai-Klear/Klear-46B-A2.5B-Base

Kwai-Klear/Klear-46B-A2.5B-Instruct

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

Kwai-Klear/Klear-Reasoner-8B

Kwai-Klear/RLEP_dataset

RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning

Kwai-Klear/qwen2.5-math-rlep

AI & ML interests

Recent Activity

Team members 9

Kwai-Klear 's collections 6