Expressiveness is central to speech-to-speech translation (S2ST), yet existing datasets rarely align source and target speech jointly in content, prosody, timing, and speaker identity. Consequently, current systems often rely on indirect conditioning or transfer mechanisms. To obtain this supervision, we introduce a training-data construction strategy that combines professional dubbing, which provides human-performed correspondence in content, prosody, and timing, with multilingual voice conversion to reduce speaker mismatch. We evaluate this supervision using existing expressive S2ST systems and DirectS2ST, an end-to-end method developed in this work that predicts the complete target-speech representation directly from source speech. Experiments on English-German and English-Spanish show that holistic parallel supervision improves expressive realization across all evaluated systems. DirectS2ST exhibits the largest gains in content, prosody, timing, speaker similarity, and human-rated expressiveness. To our knowledge, this work provides the first systematic investigation of holistic parallel supervision for expressive S2ST.
Automated detection of machine-generated text is applied where the verdict carries a cost for the author, yet origin is a property of the production process, not an observable property of the text. The conditions under which a text is produced push it in the same direction in which a generative model is presumed to push it. This study measures the contribution of these conditions while origin is held fixed. The Russian-language corpus of 1882 documents comprises a machine part, generated by four generation channels (each backed by its own model family) across 45 tasks in three task modes, and an archival human part annotated for source regimentation level before the texts were read. The primary contrast is computed within the machine corpus: both halves of a pair are generated by the same model for the same task and differ only in task wording. Machine-likeness is measured by four operationalisations: an interpretable index with weights fixed before data collection, a trained classifier, a zero-shot metric on an open model, a judge model. The main result is disagreement between procedures: changing the task mode shifted the scores of all four, but three gave a negative shift, the judge a positive one, and none of the four intervals covers zero. The comparison plan and the specifications of procedures 2-4 were fixed after the result of procedure 1, before procedures 2-4 ran; the disagreement survived correction of a corpus defect and of the nested validation. A baseline on the source identifier alone reaches a median AUROC of 1.0000 on the thirteen group splits where it is defined, and removing emphasis markers flipped a confident machine verdict to human without changing the full text by a single character. The scores are properties of a specific measurement system and corpus: they reflect data collection, repetition, formatting, and preprocessing decisions as well as linguistic style.
Layer3 Intel – 4 Nov 26 Residential Proxies Detected on White House Network Our new Residential Proxy Observatory shows residential proxy traffic exiting the White House network: 236 times in 30 days, through 28 public proxy services. 专注研究住宅代理的 Layer3 Intel 最近发现白宫 ASN 有代理流量,IP 在 28 个住宅代理提供商的池子里。。。 有佬研究这种渠道怎么整,能锁定 IP 吗?这种 IP 注册的 claude 号大概很硬吧
大致考虑分为三类: 一类是轮子型的,需要长期迭代,高度关注安全性,需要人背锅的项目。这种坚持古法编程、结对 code review 。 第二类是常规项目,一半 ai 开发,一般人工编写、code review ,需要效率和可控兼备。 第三类是全面 ai 化,人工只负责许愿。ai 开发、ai 审核、ai 测试、ai 运维等全套。 这一年多严重依赖 AI 编程,被 ai 带来的智商碾压,也发现 ai 的破坏力同样的更强的,不知道大佬们是不是已经驯服 ai 了,还是被 ai 驯服了?
最近做了个有点不一样的逆向工程 Agent 。想解决的其实是个很实际的问题:逆向任务一复杂,AI 很容易跑偏,或者分析到一半就说自己搞定了。目前基于强化学习牵引所以目前支持 WEB 、PE 、ELF 、APK 、固件等方向,可以一边学习一边分析,也会把做过的方法和结果沉淀下来,后续任务能继续积累经验。项目还在迭代,欢迎对 AI 逆向感兴趣的朋友试试,也欢迎直接拿真实样本来交流和 star 。GitHub: https://github.com/amd2g2zz/kunglao-agent
Decision models choose among predefined options in tasks such as routing and action selection. In multi-agent collaboration, a decision determines how members divide work, exchange resources, and act in parallel. We introduce TandemBench, a benchmark of 1,200 questions in multi-agent cooking scenarios where coordination choices affect goal completion. Models receive complete global information and candidate team plans, with reference answers established through execution and exact search. Models select an optimal team plan and, in paired variants that retain or remove it, judge whether better arrangements exist beyond the supplied options. We evaluate 40 native decision models and compare them with 10 general-purpose language models. The best native decision model achieves 62.50% decision accuracy. Native decision models remain close to chance in optimality verification. Paired tests reveal that some report better alternatives regardless of whether an optimal plan is already present. These findings show that team-plan decision accuracy alone can conceal systematic errors in judging whether the supplied options contain an optimal arrangement. The dataset and evaluation code are publicly available at https://github.com/lililibaohang/TandemBench.