我的收藏提交工具
FOXAI SEARCH

全站搜索

新闻报道 462

Tencent Hy4 now available on AI Gateway

Hy4, Tencent's latest AI model with vision capabilities, is now available on Vercel's AI Gateway at 50% off through December 31, 2026. It supports reasoning, tool calling, structured outputs, image input, and a 1M-token context window. Hy4 excels in detailed image analysis, complex chart reading, and computer use across command-line and graphical interfaces. It outperforms its preview version in instruction following, long-context handling, and deep research tasks. Users can access it via the model name 'tencent/hy4' in supported tools like Claude Code, Codex, and Cursor after setting up the Vercel CLI. AI Gateway offers unified API access, usage tracking, cost management, and performance optimizations with no markup or platform fees.

翻译服务暂未运行,当前显示原文。
Vercel

在安装前及安装过程中阻止恶意 npm 包

Vercel 现在通过动态黑名单,在构建过程中及依赖安装前主动检查并阻止恶意 npm 包,从而防止有害脚本执行。该系统会扫描受支持的锁定文件和公共 npm 下载;如果检测到被阻止的包,将自动中止部署,同时识别出问题包及其版本,并尝试使构建缓存失效。用户必须更新到安全的依赖版本并重新生成锁定文件后才能重新部署。这些安全措施会自动应用于所有套餐,无需任何配置。

尚无对应语言译文,当前显示原文。
Vercel

用于公平深度伪造检测的交叉性不变学习

arXiv:2610.37881v1 发布类型:新 摘要:深度伪造检测模型虽然整体准确率较高,但在不同人口统计群体之间却表现出显著的性能差异,导致某些群体的假阳性率远高于其他群体。现有的公平性感知方法通过约束模型输出以实现各群体预测的一致性来应对这一问题,但并未解决潜在的特征层面偏见。因此,这些模型仍可能依赖于诸如皮肤纹理等人口统计学特征作为检测篡改内容的间接线索。为了解决这一问题,我们提出了交叉性不变学习(IIL)框架,该框架着重改进特征学习,而非仅仅调整模型输出。IIL通过交替识别最具挑战性的群体划分

arXiv cs.CV

制品蒸馏:无需训练的前沿模型到小型语言模型的迁移

arXiv:2610.37680v1 发布类型:新 摘要:缩小前沿模型与小型语言模型之间的差距,通常采用蒸馏方法:在前沿模型(教师)的输出上对小型模型(学生)进行微调,但这使得迁移过程依赖于训练计算,并且被迁移的知识往往难以解释。我们提出了一种名为“制品蒸馏”的方法:由教师模型解决一系列训练实例,并将其求解过程外化为一个制品库,学生在推理时直接查询该库,而无需进行梯度更新。在四项LiveBench任务中,由Claude Opus 4.5构建的制品库使Claude Haiku 4.5在空间推理任务上的表现(0.707 vs. 0.647)达到其自身成本的60%时,已超越未借助任何辅助的Claude Sonnet 4.5;而在表格连接任务上,该制品库仅以Sonnet 4.5成本的89%便达到了相同水平。同样的原始制品库还提升了

arXiv cs.CL

Simplifying runtime caching on Vercel

Vercel is merging its Data Cache service into Runtime Cache, unifying data caching across frameworks like Next.js, SvelteKit, and Nuxt. Developers using fetch caching or unstable_cache in Next.js won’t need to change their code. Pro and Enterprise projects receive increased storage allocations, with Pro getting 8x more space and Enterprise 10x. Runtime Cache now handles regional storage, authentication, and tag-based invalidation across Vercel’s global infrastructure. Improvements include faster reads during traffic bursts via circuit breakers, higher storage budgets reducing evictions, and enhanced observability with deployment markers, revalidation causes, and write utilization metrics. The migration simplifies billing and usage tools, with existing teams receiving advance notice and pricing details.

翻译服务暂未运行,当前显示原文。
Vercel

The fx adapter now runs the harness on the host

The fx adapter for the AI SDK’s HarnessAgent now uses libfx, enabling the harness and model requests to run in the application’s process while keeping filesystem and shell operations isolated in a sandbox. This update simplifies setup by eliminating the need to install fx in the sandbox, run a bridge, or expose a port. Model credentials remain on the host. New features include built-in tool filtering, mid-turn steering, structured output, image tool results via toModelOutput(), and session resumption across host processes. Update @ai-sdk/harness-fx to the latest version to access these improvements.

翻译服务暂未运行,当前显示原文。
Vercel

Google introduces cutting-edge Genie 4 world model

Google LLC today previewed Genie 4, an artificial intelligence model that can generate realistic three-dimensional environments. The algorithm is the latest addition to a series of world models that the company launched in 2024. Compared to its predecessor, Genie 4 is better at rendering fluid movements and other complex details. Furthermore, it can generate accompanying […] The post Google introduces cutting-edge Genie 4 world model appeared first on SiliconANGLE.

翻译服务暂未运行,当前显示原文。
SiliconANGLE AI

b11946

server : add realtime conversation and transcription on /v1/realtime (#31269) * server : add realtime conversation and transcription on /v1/realtime Co-authored-by: Xuan Son Nguyen Assisted-by: Claude Opus 5.5 * examples : default the realtime client to the server port 9931 Assisted-by: Claude Opus 5.5 * server : sample realtime responses right after their own decode Slots respond in turns on one context: sampling at the start of the next step read the logits of whichever slot decoded last, so concurrent sessions mixed their outputs. Assisted-by: Claude Opus 5.5 * move more stuff to server-realtime, making it self-contained * examples : fix the type check of the realtime client Assisted-by: Claude Opus 5.5 * examples : use the model card prompts in the realtime client Assisted-by: Claude O

翻译服务暂未运行,当前显示原文。
llama.cpp 发布

先检测再消歧:基于扰动的大型语言模型输入歧义检测

arXiv:2610.36353v1 发布类型:新 摘要:大型语言模型(LLMs)常常将含糊的输入当作具有单一明确含义来回答。这存在严重问题,因为输入歧义是不确定性的一个上游来源:当一个提示可能存在多种有效解释时,关键问题在于模型是否应当直接作出回应。现有的输入不确定性方法通常依赖于由大型语言模型生成的语句或澄清,但这类转换可能在测量歧义之前就已经对输入进行了消歧。我们提出了一种保留标签的扰动框架,用于检测输入歧义,在该框架中,扰动保持与原始输入相近,同时保留其标签。我们通过两种检测器对该原则进行了具体实现:一种是基于规则的黑盒扰动库

arXiv cs.CL

INC-MoE: Overlapping In-Network Collectives and Expert Computation for Expert-Parallel Mixture-of-Experts Inference

arXiv:2610.36339v1 Announce Type: new Abstract: In expert-parallel mixture-of-experts (MoE) serving, dispatch moves tokens to the accelerators hosting their selected experts, and combine returns expert outputs to each token's owner. Both operations lie on the critical path and can dominate MoE layer latency in multi-node deployments. We present INC-MoE, an expert-parallel MoE layer that offloads dispatch and combine to the network switch and overlaps both collectives with each other and with expert computation. Dispatch uses in-network AllGather through switch-side multicast, while combine uses in-network ReduceScatter through switch-side reduction. Both collectives use message semantics between the end hosts and the switch. Because the in-network collectives load opposite directions of ea

翻译服务暂未运行,当前显示原文。
arXiv cs.DC