KnowledgeXLab@Shanghai AI Lab

community

https://knowledgexlab.github.io/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

fudaocheng new activity about 3 hours ago

KnowledgeXLab/P-OPD_Experiments:Add Qwen3-4B-Math-SFT for A2-OPD

fudaocheng new activity about 3 hours ago

KnowledgeXLab/P-OPD_Experiments:Add Qwen3-4B-Math-GRPO-Early-RL for A2-OPD

Edaizi new activity about 13 hours ago

KnowledgeXLab/P-OPD_Experiments:Add Qwen3-4B-Math-GRPO-Early-RL for A2-OPD

View all activity

Papers

MemHarness: Memory Is Reconstructed, Not Replayed

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

View all Papers

KnowledgeXLab 's papers 3

Submitted by

Rong Wu

MemHarness: Memory Is Reconstructed, Not Replayed

KnowledgeXLab

KnowledgeXLab@Shanghai AI Lab

Submitted by

Fu

Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

KnowledgeXLab

KnowledgeXLab@Shanghai AI Lab

Submitted by

Licheng Wen

Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks

KnowledgeXLab

KnowledgeXLab@Shanghai AI Lab