Biography
PhD student at UW-Madison working on test-time training, efficient LLM architecture, and long-context memory.
Sitemap
All English pages and posts on this site. An XML sitemap is also available for search engines.
Pages
Posts
Is the LLM Value Chain the Next Apple Supply Chain? Profits, Capital, and Global Specialization
Published:
Comparing the Apple and LLM value chains through financial filings, official disclosures, and interviews: from chips, manufacturing, and cloud to data startups in Silicon Valley and Beijing and UniPat’s approach to tasks and evaluation, with a focus on profits, capital investment, and customer dependence.
When AI Reaches the Limits of Human Understanding: Echoes of Frontier Physics
Published:
Frontier physics has long required mathematics, instruments, and large collaborations to make sense of the world. Frontier AI is raising a similar question: when capabilities grow faster than our understanding, how do we check reasoning we can no longer follow from beginning to end?
Policy Consistency for Recurrent Models in RL: Why LastKV Places Feedback at Chunk Boundaries
Published:
Why can parallel prefill, token-by-token recurrent rollout, and fully parallel policy replay define different policies? A look at LastKV’s fixed chunk recurrence through probability and gradient consistency in RL.
Why Models Drift: From LLM Reinforcement Learning to Autoregressive Video
Published:
From Score Centering, BPO, and MaxRL to Self Forcing, video preference optimization, and KV quantization correction: understanding drift across domains through distributions, feedback loops, and points of intervention.