论文 on Blowfishhttps://huggingaha.github.io/tags/%E8%AE%BA%E6%96%87/Recent content in 论文 on BlowfishHugo -- gohugo.iozh-cnhuggingaha@gmail.com (时影)huggingaha@gmail.com (时影)© 2026 时影Wed, 31 Dec 2025 00:00:00 +0000Agent 系统中“压缩器-预测器”的信息瓶颈与 Scaling Lawhttps://huggingaha.github.io/blogs/agent/information-theoretic-perspective-on-agentic-system-design/Wed, 31 Dec 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/agent/information-theoretic-perspective-on-agentic-system-design/Youtu-GraphRAG：垂直统一的图增强推理RAGhttps://huggingaha.github.io/blogs/rag/youtu-graphrag/Fri, 26 Dec 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/rag/youtu-graphrag/LatentMAS：当大模型学会“脑对脑”直接通信https://huggingaha.github.io/blogs/agent/latent-collaboration-in-multi-agent-systems/Sat, 06 Dec 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/agent/latent-collaboration-in-multi-agent-systems/构建鲁棒的 AI 系统：Context Engineering 2.0中的分层记忆、隔离与协调https://huggingaha.github.io/blogs/agent/context-engineering-2.0/Fri, 07 Nov 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/agent/context-engineering-2.0/MBTI-in-Thoughts：基于MBTI的LLM行为调控与结构化思维框架https://huggingaha.github.io/blogs/llm/mbti-in-thoughts-psychologically-enhanced-ai-agents/Tue, 30 Sep 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/llm/mbti-in-thoughts-psychologically-enhanced-ai-agents/译文-Small Leak Can Sink a Great Ship—Boost RL Training on MoE with 𝑰𝒄𝒆𝑷𝒐𝒑!https://huggingaha.github.io/blogs/llm/small-leak-can-sink-a-great-ship-boost-rl-training-on-moe-with-icepop/Tue, 23 Sep 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/llm/small-leak-can-sink-a-great-ship-boost-rl-training-on-moe-with-icepop/REFRAG：Rethinking RAG based Decodinghttps://huggingaha.github.io/blogs/rag/refrag-rethinking-rag-based-decoding/Fri, 12 Sep 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/rag/refrag-rethinking-rag-based-decoding/Why Language Models Hallucinate——解构LLM幻觉https://huggingaha.github.io/blogs/llm/llm-hallucinate/Sun, 07 Sep 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/llm/llm-hallucinate/LLM幻觉不可避免？https://huggingaha.github.io/blogs/llm/llm-hallucinations-taxonomy/Sat, 16 Aug 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/llm/llm-hallucinations-taxonomy/上下文学习中的“位置效应”https://huggingaha.github.io/blogs/agent/bicl-prompt-positional-bias/Fri, 01 Aug 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/agent/bicl-prompt-positional-bias/GSPO：组序列策略优化https://huggingaha.github.io/blogs/llm/gspo-rl-llm/Mon, 28 Jul 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/llm/gspo-rl-llm/kimi-k2技术报告https://huggingaha.github.io/blogs/llm/kimi-k2-technical-report/Tue, 22 Jul 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/llm/kimi-k2-technical-report/Context Engineering综述解读https://huggingaha.github.io/blogs/agent/context-engineering-survey/Sat, 19 Jul 2025 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/agent/context-engineering-survey/GIB与AD-GCL如何打造更鲁棒的GNNhttps://huggingaha.github.io/blogs/kg/modular-manifolds-thinking-machines/Sun, 09 Oct 2022 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/kg/modular-manifolds-thinking-machines/TransAE：基于多模态数据增强的知识图谱表示学习https://huggingaha.github.io/blogs/kg/transae-multimodal-data-enhanced-representation-learning/Wed, 05 Oct 2022 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/kg/transae-multimodal-data-enhanced-representation-learning/FAME：高效处理大规模属性化多重异构网络https://huggingaha.github.io/blogs/kg/fame-spectral-graph-transformation-fast-random-projection-embedding/Tue, 09 Aug 2022 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/kg/fame-spectral-graph-transformation-fast-random-projection-embedding/RAHMeN：当图网络学会“关注”复杂关系https://huggingaha.github.io/blogs/kg/rahmen-multi-embeddings/Mon, 01 Aug 2022 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/kg/rahmen-multi-embeddings/SSN_GATNE-T：基于GATNE的精细化改进与探索https://huggingaha.github.io/blogs/kg/ssn_gatne-t-vs-gatne-t/Mon, 25 Jul 2022 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/kg/ssn_gatne-t-vs-gatne-t/GATNE：面向属性、多重、异构网络的统一表示学习框架https://huggingaha.github.io/blogs/kg/gatne-representation-learning-for-attributed-multiplex-heterogeneous-network/Fri, 22 Jul 2022 00:00:00 +0000huggingaha@gmail.com (时影)https://huggingaha.github.io/blogs/kg/gatne-representation-learning-for-attributed-multiplex-heterogeneous-network/