Yuxin Zhang

Diffusion models can learn new objectives by stochastically routing attention within their existing architecture, achieving 4x faster RL training without sacrificing generation quality.

Enforcing uniform load balancing across video tokens fundamentally breaks visual coherence, but bifurcating experts into semantic and generic tiers resolves patch fragmentation while driving emergent coarse-to-fine denoising.

Autonomous model post-training can outperform human-crafted instruct baselines on hard coding benchmarks while completely eliminating reward hacking once experimental exploration is governed by a sandboxed OS and a dynamic peer-review DAG.