CCTest · Blog
Compile by Training Turns Natural-Language Specs into Local Neural Functions
Frameworks & Tools
cctest.ai

Compile by Training Turns Natural-Language Specs into Local Neural Functions

Compile by Training extends Program-as-Weights with a training-based compilation mode: teacher models synthesize examples, then a lightweight adapter specializes a compact local interpreter. The approach improves semantic accuracy on a hard benchmark subset, while increasing compile-time cost and raising questions about coverage.

Read more
CCTest · Blog
A New Metric Asks How Much Speech a Brain-Computer Interface Can Really Communicate
Evaluation & Benchmarks
cctest.ai

A New Metric Asks How Much Speech a Brain-Computer Interface Can Really Communicate

Speech brain-computer interfaces are often evaluated under incompatible vocabularies, datasets, and metrics. A new measure called open-vocabulary mutual information, or OVMI, accounts for both decoding accuracy and the share of a user’s intended language that a system can support.

Read more
CCTest · Blog
Robots Cannot Wait for Inference: SmoothRL Aligns Online RL with Asynchronous Execution
Reinforcement Learning
cctest.ai

Robots Cannot Wait for Inference: SmoothRL Aligns Online RL with Asynchronous Execution

Astribot’s SmoothRL framework addresses a basic mismatch in robot learning: an action chunk generated by a large model is not necessarily the chunk the robot executes. It updates the policy only on actions that actually enter the physical trajectory.

Read more