在小型芯片上部署AI模型，Edge Impulse让你从云端到边缘一步到位，专为低功耗设备优化。
Article URL: https://www.easelinktech.com/why-every-electronic-product-may-need-to-be-rebuilt-for-on-device-ai-the-chip-layer-will-decide-the-next-har…
重新审视大模型剪枝后微调的必要性，挑战复杂剪枝标准，提出更高效的压缩策略。
arXiv:2510.14444v3 Announce Type: replace Abstract: Post-training pruning can substantially reduce LLM inference costs, but it often degrades quality …
提出CRAFT方法解决联邦学习中客户端模型更新冲突，通过冲突消解聚合提升训练效率与模型质量。
arXiv:2605.21317v1 Announce Type: new Abstract: The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (…
多模态大模型消除幻觉新方法：锐度感知鲁棒擦除，超越浅层遗忘，提升模型可靠性
arXiv:2601.16527v2 Announce Type: replace Abstract: Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entit…
8B模型被Forge从53%拔高到99%？这个开源护栏工具还顺带抬升了Sonnet的表现。
Hi HN, I'm Antoine Zambelli, AI Director at Texas Instruments. I built Forge, an open-source reliability layer for self-hosted LLM tool-calling. What …
Google推出Gemini 3.5 Flash，速度突破让生成式AI真正落地，Agent优化和Omni模型同步亮相。
Google says its more efficient Gemini 3.5 Flash is the key to your agentic AI future.
教你如何让小型语言模型学会判断何时该“求救”，避免盲目依赖昂贵大模型，提升Agent系统效率的突破性研究。
arXiv:2605.16604v1 Announce Type: new Abstract: Efficient agentic systems should incur expensive frontier-model costs only on decisions where a cheape…
深度解析LLM架构前沿：KV共享、多头压缩注意力等最新进展，助你把握大模型底层革新。
Article URL: https://substack.com/@rasbt/p-197933886 Comments URL: https://news.ycombinator.com/item?id=48160322 Points: 1 # Comments: 0
利用用户交互日志实现大语言模型持续学习，突破数据稀缺与算力瓶颈的新范式。
arXiv:2602.06470v2 Announce Type: replace-cross Abstract: Scaling training data and model parameters has long driven progress in large language models…
开源项目Orthrus-Qwen3实现高达7.8倍前向推理加速，且保证输出分布完全一致，Qwen3模型效率飞跃。
Article URL: https://github.com/chiennv2000/orthrus Comments URL: https://news.ycombinator.com/item?id=48154865 Points: 217 # Comments: 43
OpenAI推出GPT-5.4 mini与nano，更小更快，专攻编码、工具调用与高并发API场景。
GPT-5.4 mini and nano are smaller, faster versions of GPT-5.4 optimized for coding, tool use, multimodal reasoning, and high-volume API and sub-agent …