https://ajing.github.io/ https://ajing.github.io/about/ https://ajing.github.io/archives/ https://ajing.github.io/posts/ https://ajing.github.io/start-here/ https://ajing.github.io/topics/ https://ajing.github.io/topics/agents/ https://ajing.github.io/topics/evaluation/ https://ajing.github.io/topics/post-training/ https://ajing.github.io/topics/rlhf/ https://ajing.github.io/topics/generative-ui/ https://ajing.github.io/posts/2026-05-28-agent-eval-difficulty-trajectory-constraints/ 2026-05-28 https://ajing.github.io/posts/2026-04-13-mercor-breach-what-leaked-about-ai-training/ 2026-04-13 https://ajing.github.io/posts/2026-03-11-improving-llm-i18n-tool-use-agency/ 2026-03-11 https://ajing.github.io/posts/2026-03-08-unverifiable-rewards-rl-frontier/ 2026-03-08 https://ajing.github.io/posts/2026-03-05-instruction-following-post-training-data/ 2026-03-05 https://ajing.github.io/posts/2026-03-01-experience-augmented-icl-complement-to-rl-post-training/ 2026-03-01 https://ajing.github.io/posts/2026-01-10-tool-selection-optimization-llm-agents-at-scale/ 2026-01-10 https://ajing.github.io/posts/2026-01-03-generative-engine-optimization-geo/ 2026-01-03 https://ajing.github.io/posts/2026-01-02-ads-formats-in-llm-products/ 2026-01-02 https://ajing.github.io/posts/2026-01-02-ads-in-llm-chatbot/ 2026-01-02 https://ajing.github.io/posts/2026-01-01-generative-ui-doesnt-move-the-needle-steering-does/ 2026-01-01 https://ajing.github.io/posts/2025-12-31-rlhf-engineering-implementation/ 2025-12-31 https://ajing.github.io/posts/2025-12-31-rlhf-ppo-dpo-grpo-notes/ 2025-12-31 https://ajing.github.io/posts/2025-09-07-ae-vae-training-learnings/ 2025-09-07 https://ajing.github.io/posts/2025-09-07-user-interest-modeling-with-transformer-architectures/ 2025-09-07 https://ajing.github.io/posts/2025-05-03-ui-representation-action-execution/ 2025-05-03 https://ajing.github.io/posts/2025-04-01-generative-ui/ 2025-04-01 https://ajing.github.io/posts/2023-08-20-how-to-make-llm-serving-faster/ 2023-08-20