Research

Most world model benchmarks hand you a number and nothing else. You cannot tell whether a model failed because it rendered the wrong object, ignored the physics of a collision, or…

Scientific discovery breaks the cheap-verifier assumption that powers modern LLM reasoning. You can't run a wet-lab assay a thousand times to check a candidate's score.

Collision-free 3D spatial editing is where every current multimodal agent breaks down. That is the central finding of VibeWorlding, a framework that formalizes the problem of…

Two problems plague GUI agents in practice: training data that drifts toward cheap, short tasks, and instructions that leave too much procedural detail unstated. UI-Mate attacks…

Training a language model through a production agent harness like Claude Code or OpenClaw is harder than it sounds. The harness is opaque: it manages context, retries failed tool…

Pixel-space diffusion has a genuine appeal: no VAE bottleneck, no reconstruction ceiling, and at inference time you skip the decoder pass entirely. The problem is that nobody had…

The core bet here is that database transaction theory, specifically ACID guarantees, maps cleanly enough onto LLM agent execution to be worth engineering against directly. That…