GitHub Security Lab 发布 LLM 驱动的 Fuzzing Taskflow，自动完成 C/C++ 项目模糊测试全流程
AIHOT ·
GitHub Security Lab 的 Antonio Morales 开源了基于 Taskflow Agent 的 Fuzzing Taskflow，指向 GitHub 仓库即可自动识别入口点、编写 harness、运行 AFL++、读取覆盖报告并分诊崩溃。
原文内容 · 暂无该语言译文AI News · 2026-09-25
按采集日期（UTC）汇总已发布资讯，原文日期单独标注。
返回资讯列表Efficient MoE Training for Biological Foundation Models
NVIDIA Technical Blog ·
As language models grow, scaling dense architectures becomes increasingly expensive. In a dense transformer, every token passes through every layer, so adding... As language mod…
原文内容 · 暂无该语言译文Teaching Reinforcement Learning and Humanoid Robotics to High-School Students: An Expert-Validated Curriculum Design on a Low-Cost Open Platform
arXiv cs.RO ·
Lower cost open source robots and reinforcement learning (RL) simulation tools create new opportunities for precollege students to engage with contemporary robotics. However, tr…
原文内容 · 暂无该语言译文A bioinspired internal model-based online estimator for planar pursuit
arXiv cs.RO ·
Bioinspired feedback controls for pursuit, tracking, and collective motion are often expressed in terms of the relative configuration between interacting agents. In practice, ho…
原文内容 · 暂无该语言译文Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts
arXiv cs.CL ·
While text-based hallucination detection is well studied, reference-free detection of factual alterations in speech remains underexplored, especially for low-resource languages.…
原文内容 · 暂无该语言译文SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
arXiv cs.CL ·
Large language models are rapidly being deployed as AI tutors, yet current evaluation paradigms assess problem-solving accuracy and generic safety in isolation, failing to captu…
原文内容 · 暂无该语言译文vLLM 新增基于 Gumbel-max 的无失真文本水印功能
AIHOT ·
vLLM 宣布支持基于 Gumbel-max 算法的无失真水印，将其集成进 Model Runner v2 的采样管线，并通过 PR #54053、#56122、#56233 实现融合 GPU kernel、双键方案和上下文去重，以兼容投机解码并保持输出多样性。
原文内容 · 暂无该语言译文