2026年7月10日 技术热点总结

技术栈：JavaScript

核心介绍：An open, structured taxonomy of what children learn across the primary/elementary years — decomposed into fine-grained “micro-topics”, wired into a prerequisite graph, and aligned to national curriculum standards. Produced by Marble. > Version： v1 · Topics： 1,590 · Prerequisite edges： 3,221 · Subjects： 8

项目数据：⭐ 1,354 Stars，🍴 261 Forks

项目简介：A native macOS UI for Apple’s platform

技术栈：Swift

核心介绍：> A *davit* is the shipboard crane that hoists cargo and small craft over the side — which is more or less what this app does with your containers. Built entirely in SwiftUI (no Electron, no web views). Davit links Apple’s own the same wire path the container CLI uses. The CLI binary is never invoked: lists, lifecycle, live stats, log streaming, image pulls, volume/network management, the in-terminal shell (davit exec), and even launchd service bootstrap all go through the API.

关键特性：Dashboard — service status …

项目简介：Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。

技术栈：TypeScript、a-stock、ai-agent、dashboard、fastapi、fintech、hk-stocks、investment-research、llm

核心介绍：> Vibe-Research: Your Personal Trading Research Agent · A股 / 美股 / 港股 的个人投研 Agent。 > 每日复盘、资讯雷达、个股数据、自选股、板块中心、我的持仓、我的研报、研究记录。把数据和功能配齐，由你自己的 AI 驱动投资研究。 Vibe-Research 是一个开源的「个人 AI 投研看板」，主推 A 股、兼看美股 / 港股（A 股常要看隔夜外围脸色，数据配上更全）。它不替你做决定——把行情、研报、估值、财务、公告、资金面、资讯都配齐，放进一个干净的看板，再留一个能接入你自己的 AI 的接口。方向和结论，交给你自己配置的模型 / agent。

项目数据：…

项目简介：Self-supervised learning for spatial perception

技术栈：Python

核心介绍：LingBot-Vision: Vision Pretraining for Dense Spatial Perception Boundary-centric masked modeling. Each row shows the input image, the PCA projection of frozen patch tokens, teacher-discovered boundary tokens, and cosine-similarity maps from selected boundary-token queries. The features capture semantic grouping and geometric structure at the same time. LingBot-Vision learns boundaries, shapes, and semantic regions all together, making it a drop-in visual encoder for dense downstream tasks:

项目数据：⭐ 576…

项目简介：Infinite Worlds with Versatile Interactions

技术栈：Python

核心介绍：Infinite Worlds with Versatile Interactions We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. The real-time version of LingBot-World-Infinity is available on two platforms. We thank Reactor and LingGuang for their support:

项目数据：⭐ 564 Stars，🍴 11 Forks

Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a result, these models can be difficult to use for planning or policy extraction. To address these limitations, we propose RoboTALES, a single-stage framework that learns task-aligned simulated futures and uses them to train robot policies. Our approach introduces two key innovations: (1) a hierarchical LLM-based planner that breaks complex tasks into a sequence of subgoals to guide the model's imagination; and…

Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to spend a pretraining budget remain poorly understood. We present the largest controlled scaling study for EO to date: 395 training runs on 1,024 GH200 superchips within a fixed pixel-wise Barlow Twins family, each evaluated on 15 downstream tasks. We find that pretraining loss barely predicts downstream performance (|Pearson r| < 0.2), so selecting models by loss wastes a large share of the compute. We also find t…

Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipulation, where success significantly depends on local force and contact geometry. Tactile sensing provides these complementary signals, yet tactile data remain costly to collect and hard to generalize across sensors, robots, and tasks. We introduce OmniTacTune, a policy-agnostic real-world RL pipeline that adapts tactile feedback to pretrained visual policies through residual correction. OmniTacTune uses a two-stage design: it first bootstraps …

Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization of breast abnormalities. However, existing multi-view learning approaches typically rely on feature-level aggregation or single-stage cross-attention, which can entangle view-specific and shared representations and restrict interaction to limited network depths. To address these limitations, we propose a token-centric dual-view learning framework that unifies prompt-based…

We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit — did the task pass? — but the people who actually use these agents experience the entire trajectory: how the agent follows instructions, uses its tools, verifies its own work, recovers from mistakes, and talks to them along the way. AgentLens evaluates that whole trajectory. It pairs formal verification, where an objective check exists, with LLM-written trajectory reviews and side-by-side comparisons, so that each run yields a readable explanation of …

Touch supplies the physical grounding needed to perceive intrinsic material properties, such as friction and compliance, that vision alone often cannot resolve. Recent efforts for equipping multimodal LLMs with this tactile sense, however, expose a zero-sum trade-off: the limited parameter budget of compact models forces a choice between acquiring the new sensory modality and preserving the established vision-language reasoning. We present Splash, a mask-isolated tactile alignment learning framework for MLLMs. Splash quantifies the significance of each pretrained parameter, and partitions t…