Representation alignment speeds up diffusion transformer training by pulling an intermediate block of the model (student) toward features of a frozen pretrained encoder (teacher). Which teacher layer to align, and for how long, is still set by convention, and each alternative costs a training run. We find that alignmen...
Yong-Cong Wang, Hingchin Chen, Ming-Yu Fan et al.· 0 citations
A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the balance stays unverified. We formalize legal ju...
Zheng-Kai Tu, Ming-Da Zhang, Zi-Jia Wang et al.· 0 citations
This work proposes CollabFlow, an RSI system of Learned Agent Collaboration: a trainable Collab-Director constructs teams of complete Agents, a frozen executor runs them, and each round's outcomes retrain the director, and each round's outcomes retrain the director.
R$^2$ Flow is introduced, a recursive self-improvement framework that alternates policy learning, independent verification, and versioned skill-library updates on a shared-state orchestration graph that improves task accuracy and library-edit precision over heuristic orchestration, reinforcement learning, and skill-evo...
Ming-Da Zhang, Qian-Shuo Huang, Yan-Jin Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.