We have 3 of 3 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Bole is presented, a kernel--runtime co-design that enables efficient tree speculation for hybrid-attention LLMs and couples efficient state management with a batch-wide verification budget calibrated to the complete hybrid forward.
Results show that template-anchored decomposition and stage-specific GPU execution can scale matrix completion beyond device-memory capacity, and show that template-anchored decomposition and stage-specific GPU execution can scale matrix completion beyond device-memory capacity.
This work proposes Test-aware Policy Refinement (TaPR), a framework that transforms execution feedback into a dense per-turn test-pass-ratio reward under a consistent multi-turn interaction protocol and a turn-aware evaluation protocol that decouple first-shot generation quality from multi-turn repair competence.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
