https://lilfry09.github.io/tags/adaptive-compute/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/categories/ai/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/ai/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/categories/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/early-exit/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/tags/latent-reasoning/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/looped-transformer/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/ai/looped-transformer-elastic-depth-post-training/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/tags/loopformer/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/tags/post-training/2026-08-18T13:38:45+08:00weekly1https://lilfry09.github.io/tags/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/categories/%E8%AE%BA%E6%96%87%E9%98%85%E8%AF%BB/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/diary/the-dark-knight-unfinished-review/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/series/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/%E8%9D%99%E8%9D%A0%E4%BE%A0/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/%E7%94%B5%E5%BD%B1/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/%E9%9A%8F%E6%84%9F/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/categories/%E6%9C%AA%E5%AE%9A%E7%A8%BF/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/series/%E6%9C%AA%E5%AE%9A%E7%A8%BF/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/distillation/2026-08-09T21:30:00+08:00weekly0.9https://lilfry09.github.io/tags/on-policy-distillation/2026-08-09T21:30:00+08:00weekly0.9https://lilfry09.github.io/tags/search-distillation/2026-08-09T21:30:00+08:00weekly0.9https://lilfry09.github.io/tags/self-distillation/2026-08-09T21:30:00+08:00weekly0.9https://lilfry09.github.io/tags/verifier/2026-08-09T21:30:00+08:00weekly0.9https://lilfry09.github.io/tags/%E8%AE%BA%E6%96%87%E9%98%85%E8%AF%BB/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/ai/distillation-beyond-compression-research-map/2026-08-09T21:30:00+08:00weekly0.9https://lilfry09.github.io/tags/kl/2026-08-09T21:00:00+08:00weekly0.9https://lilfry09.github.io/tags/on-policy/2026-08-09T21:00:00+08:00weekly0.9https://lilfry09.github.io/tags/opd/2026-08-09T21:00:00+08:00weekly0.9https://lilfry09.github.io/tags/rl/2026-08-09T21:00:00+08:00weekly0.9https://lilfry09.github.io/tags/sft/2026-08-09T21:00:00+08:00weekly0.9https://lilfry09.github.io/ai/sft-rl-opd-on-policy-data/2026-08-09T21:00:00+08:00weekly0.9https://lilfry09.github.io/tags/agent-training/2026-08-06T20:00:00+08:00weekly0.9https://lilfry09.github.io/tags/benchmark/2026-08-06T20:00:00+08:00weekly0.9https://lilfry09.github.io/tags/coding-agent/2026-08-06T20:00:00+08:00weekly0.9https://lilfry09.github.io/tags/fullstack-agent/2026-08-06T20:00:00+08:00weekly0.9https://lilfry09.github.io/ai/fullstack-agent-data-construction/2026-08-06T20:00:00+08:00weekly0.9https://lilfry09.github.io/tags/%E6%95%B0%E6%8D%AE%E5%90%88%E6%88%90/2026-08-06T20:00:00+08:00weekly0.9https://lilfry09.github.io/tags/agent/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/tags/agentenv/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/ai/agentenv-agentic-rl-environment-infrastructure/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/tags/agentic-rl/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/tags/firecracker/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/tags/overlaybd/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/tags/sandbox/2026-08-05T23:30:00+08:00weekly0.9https://lilfry09.github.io/tags/attention/2026-07-28T00:00:00+08:00weekly0.7https://lilfry09.github.io/tags/linear-attention/2026-07-28T00:00:00+08:00weekly0.7https://lilfry09.github.io/tags/long-context/2026-07-28T00:00:00+08:00weekly0.7https://lilfry09.github.io/tags/transformer/2026-07-28T00:00:00+08:00weekly0.7https://lilfry09.github.io/ai/linear-attention-from-scratch/2026-07-28T00:00:00+08:00weekly0.7https://lilfry09.github.io/tags/claude-code/2026-07-20T21:30:00+08:00weekly0.6https://lilfry09.github.io/tags/swe/2026-07-20T21:30:00+08:00weekly0.6https://lilfry09.github.io/tags/trajectory/2026-07-20T21:30:00+08:00weekly0.6https://lilfry09.github.io/ai/long-horizon-swe-agent-training/2026-07-20T21:30:00+08:00weekly0.6https://lilfry09.github.io/tags/agent-data/2026-07-14T20:20:00+08:00weekly0.6https://lilfry09.github.io/ai/swe-agent-benchmark-data-report/2026-07-14T20:20:00+08:00weekly0.6https://lilfry09.github.io/tags/swe-bench/2026-07-14T20:20:00+08:00weekly0.6https://lilfry09.github.io/ai/coding-agent-latest-research-survey/2026-07-14T03:30:00+08:00weekly0.5https://lilfry09.github.io/tags/terminal/2026-07-14T03:30:00+08:00weekly0.5https://lilfry09.github.io/tags/async-rl/2026-07-13T23:30:00+08:00weekly0.5https://lilfry09.github.io/tags/grpo/2026-07-13T23:30:00+08:00weekly0.5https://lilfry09.github.io/tags/llm/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/ppo/2026-07-13T23:30:00+08:00weekly0.5https://lilfry09.github.io/tags/seer/2026-07-13T23:30:00+08:00weekly0.5https://lilfry09.github.io/ai/async-rl-policy-staleness-global-barrier/2026-07-13T23:30:00+08:00weekly0.5https://lilfry09.github.io/tags/composer/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/diffusion-language-model/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/dllm/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/dllm-method-survey/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/llada/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/masked-diffusion/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/moe/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/r3/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/r3-async-rl-moe-routing-replay/2026-07-13T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/deepseek/2026-07-11T23:50:00+08:00weekly0.5https://lilfry09.github.io/tags/dspark/2026-07-11T23:50:00+08:00weekly0.5https://lilfry09.github.io/tags/mtp/2026-07-11T23:50:00+08:00weekly0.5https://lilfry09.github.io/tags/qwen/2026-07-11T23:50:00+08:00weekly0.5https://lilfry09.github.io/tags/speculative-decoding/2026-07-11T23:50:00+08:00weekly0.5https://lilfry09.github.io/ai/qwen-bebop-deepseek-dspark-speculative-decoding/2026-07-11T23:50:00+08:00weekly0.5https://lilfry09.github.io/tags/sjtu/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E5%A4%A7%E7%89%A9/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E5%A4%A7%E5%AD%A6%E7%89%A9%E7%90%86/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E9%87%8F%E5%AD%90%E5%8A%9B%E5%AD%A6/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E9%87%8F%E5%AD%90%E7%89%A9%E7%90%86/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/posts/quantum-physics-review/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E6%9C%9F%E6%9C%AB%E5%A4%8D%E4%B9%A0/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E7%89%A9%E7%90%86/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/categories/%E5%AD%A6%E4%B9%A0/2026-05-27T12:00:00+08:00weekly0.5https://lilfry09.github.io/tags/cross-entropy/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/focal-loss/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/focal-loss-class-imbalance/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/pytorch/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E7%B1%BB%E5%88%AB%E4%B8%8D%E5%B9%B3%E8%A1%A1/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/categories/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-05-07T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/agent-framework/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/agent-runtime/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/agentic-coding/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/arxiv/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/dpo/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/groupdpo/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/ai/groupdpo-group-wise-preference-optimization/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/harness/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/mopd/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/preference-optimization/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/tags/test-time-compute/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/training-data/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/multi-teacher-on-policy-distillation-post-training-primitive/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/scaling-test-time-compute-for-agentic-coding/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/stronger-agent-models-thinner-frameworks/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/agent-harness-training-trajectory-signal/2026-05-05T00:00:00+08:00weekly0.5https://lilfry09.github.io/ai/coding-agent-data-synthesis-qwen-research/2026-04-19T20:25:00+08:00weekly0.5https://lilfry09.github.io/posts/%E6%97%B6%E4%BB%A3%E6%B4%AA%E6%B5%81%E4%B8%AD%E7%9A%84%E9%94%9A%E7%82%B9%E6%96%B0%E4%B8%80%E8%BD%AE%E7%A7%91%E6%8A%80%E9%9D%A9%E5%91%BD%E4%B8%8B%E4%BA%BA%E6%96%87%E4%B8%8E%E6%99%BA%E8%83%BD%E7%9A%84%E5%8F%8C%E5%90%91%E8%B5%8B%E8%83%BD/2026-04-13T10:30:00+08:00weekly0.5https://lilfry09.github.io/diary/%E9%A6%99%E6%B0%B4%E6%8E%A8%E8%8D%90%E7%AC%94%E8%AE%B0%E4%B8%89%E6%94%AF%E5%80%BC%E5%BE%97%E6%85%A2%E6%85%A2%E9%97%BB%E7%9A%84%E5%91%B3%E9%81%93/2026-04-12T20:55:00+08:00weekly0.5https://lilfry09.github.io/diary/%E4%B8%80%E4%BA%9B%E6%83%B3%E6%B3%95%E6%9C%89%E5%85%B3%E4%BA%8E%E4%BA%BA%E7%B1%BB%E7%9A%84%E6%9C%AC%E6%BA%90%E4%BB%A5%E5%8F%8A%E7%A4%BE%E4%BC%9A%E7%9A%84%E7%BB%84%E7%BB%87/2026-04-09T16:15:05+08:00weekly0.5https://lilfry09.github.io/tags/alignment/2026-04-08T19:35:00+08:00weekly0.5https://lilfry09.github.io/tags/ranking/2026-04-08T19:35:00+08:00weekly0.5https://lilfry09.github.io/tags/reward-modeling/2026-04-08T19:35:00+08:00weekly0.5https://lilfry09.github.io/ai/bt-vs-pl-ranking-in-alignment/2026-04-08T19:35:00+08:00weekly0.5https://lilfry09.github.io/tags/rope/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/tags/yarn/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/ai/yarn-context-window-extension/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/tags/mcmc/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/tags/reasoning/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/tags/sampling/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/ai/reasoning-with-sampling-rl-redistribution/2026-04-08T09:10:00+08:00weekly0.5https://lilfry09.github.io/tags/olmo-3/2026-04-06T19:40:00+08:00weekly0.5https://lilfry09.github.io/ai/olmo3-training-signals/2026-04-06T19:40:00+08:00weekly0.5https://lilfry09.github.io/posts/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E4%BC%98%E5%8C%96%E7%AE%97%E6%B3%95/2025-09-02T13:20:08+08:00weekly0.5https://lilfry09.github.io/categories/leetcode/2025-06-20T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E5%93%88%E5%B8%8C%E8%A1%A8/2025-06-20T00:00:00+08:00weekly0.5https://lilfry09.github.io/tags/%E6%95%B0%E7%BB%84/2025-06-20T00:00:00+08:00weekly0.5https://lilfry09.github.io/leetcode/49%E5%AD%97%E6%AF%8D%E5%BC%82%E4%BD%8D%E8%AF%8D%E5%88%86%E7%BB%84/2025-06-20T00:00:00+08:00weekly0.5https://lilfry09.github.io/leetcode/%E5%AF%BB%E6%89%BE%E9%87%8D%E5%A4%8D%E5%AD%90%E6%A0%91/2025-03-31T21:32:46+08:00weekly0.5https://lilfry09.github.io/posts/%E5%A6%82%E4%BD%95%E7%94%A8hugo%E6%9E%84%E5%BB%BA%E8%87%AA%E5%B7%B1%E7%9A%84%E5%8D%9A%E5%AE%A2/2025-03-31T13:45:08+08:00weekly0.5https://lilfry09.github.io/about/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/ai/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/leetcode/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/posts/2026-08-18T14:02:32+08:00weekly1https://lilfry09.github.io/diary/2026-08-18T14:02:32+08:00weekly1