按本站收录日期（UTC）归档，不代表事件发生于当天；原公告、聚合源发布与收录时间分别标注。
返回资讯列表NVIDIA Technical Blog ·
Preparing CAD assets for robotics simulation requires more than converting geometry to OpenUSD: developers must configure and validate materials, collision... Preparing CAD asse…
原文内容 · 暂无该语言译文AIHOT ·
ComfyUI 博客作者用智能体搜集各类优化，把 MiniMax H3 实时视频生成压缩到单张 RTX 5090（32 GB 显存）上运行，生成 30 秒视频耗时 23.51 秒，达 1.28 倍实时吞吐。
原文内容 · 暂无该语言译文arXiv cs.RO ·
Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating evidence may reside in crew…
原文内容 · 暂无该语言译文arXiv cs.CL ·
Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failure mode we term session-level …
原文内容 · 暂无该语言译文arXiv cs.RO ·
The future of autonomous robots in human-oriented environments depends on their ability to navigate in the absence of prebuilt maps; exploiting navigational aids, such as naviga…
原文内容 · 暂无该语言译文arXiv cs.CL ·
Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural des…
原文内容 · 暂无该语言译文AIHOT ·
ts-rust（tsc-rs）将 microsoft/TypeScript（Go 实现）的编译器、类型检查器和语言服务器移植为 Rust，作者称全部代码由 LLM 编写，本人未读过代码。
原文内容 · 暂无该语言译文NVIDIA Technical Blog ·
How we taught robots to assemble GB300 tester trays and what it taught us about robot learning, mechanical intelligence, and good old-fashioned engineering The... How we taught …
原文内容 · 暂无该语言译文AIHOT ·
Unsloth 发布教程与开源仓库，可将 Qwen3.8、Gemma 4 等 LLM 微调为输出选项概率的决策模型，Qwen3.5 0.8B 在 3 个决策基准上的合计准确率从 20.7% 提到 74.3%，仅需 4GB 显存。
原文内容 · 暂无该语言译文AIHOT ·
作者基于为跨公司工作的 Agent 构建记忆系统一年的经验指出，AI 失败的常见原因不是模型推理差，而是它看不到关键决策上下文，多数 agent memory 只是给瞎子更大的档案柜。
原文内容 · 暂无该语言译文
