CCTest · Blog
SAF-OPD: A More Stable Way to Combine RLVR and On-Policy Distillation
Reinforcement Learning
cctest.ai

SAF-OPD: A More Stable Way to Combine RLVR and On-Policy Distillation

SAF-OPD tackles a subtle failure mode in LLM post-training: reinforcement learning with verifiable rewards and on-policy distillation are complementary, but a fixed mixture can collapse entropy and suppress exploration. The proposed SAF framework regulates when and how strongly the teacher signal is used.

Read more
CCTest · Blog
CS-JEPA: A Decentralized Way for Swarm Robots to Predict a Shared Future
Robotics & Physical AI
cctest.ai

CS-JEPA: A Decentralized Way for Swarm Robots to Predict a Shared Future

A new paper introduces Collective-State JEPA, a decentralized predictive architecture that lets each robot in a swarm form a representation of the same future collective state. The results highlight label efficiency, topology transfer, and planning-relevant value estimation.

Read more