CCTest · Blog
UniWAM Unifies Physical Reasoning, World Modeling, and Robot Action
Robotics & Physical AI
cctest.ai

UniWAM Unifies Physical Reasoning, World Modeling, and Robot Action

UniWAM presents a unified world-action model that combines physical reasoning, visual world generation, and action prediction in one training framework. It brings together human egocentric videos, robot demonstrations, and visual question answering data to improve embodied understanding and control.

Read more
CCTest · Blog
Giving AI 50 Million Tokens of Reusable Memory Through Persistent KV State
Memory & Context
cctest.ai
Memory & Context

Giving AI 50 Million Tokens of Reusable Memory Through Persistent KV State

An experiment with galahad-kv shows that a model’s key-value state can be stored on encrypted local NVMe and loaded later without recomputation. The approach does not create a wider attention window, but it offers a practical way to reuse very long histories more efficiently.

Read more
CCTest · Blog
RobotWorld Tests Whether Multimodal Agents Can Actually Operate Robots
Robotics & Physical AI
cctest.ai

RobotWorld Tests Whether Multimodal Agents Can Actually Operate Robots

RobotWorld is a simulation benchmark for testing whether multimodal agents can turn instructions, visual observations, and tool use into reliable robot behavior. Its results show that agents can build sophisticated perception and control pipelines, but still struggle to maintain state, recover from failure, and verify completion.

Read more
CCTest · Blog
SWE-Game Tests Whether Coding Agents Can Build Playable Games
Evaluation & Benchmarks
cctest.ai

SWE-Game Tests Whether Coding Agents Can Build Playable Games

SWE-Game evaluates coding agents across 247 game-development tasks, from implementing mechanics to repairing faults and porting projects between engines. The results show that agents can produce playable prototypes, but still struggle with complete requirements and reliable gameplay logic.

Read more