2026年7月11日 技术热点总结

项目简介：Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

技术栈：Python、image-to-video、lingbot-video、video-generation、world-models

核心介绍：We are excited to introduce LingBot-Video, the first open-source large-scale MoE (Mixture-of-Experts) video generation model dedicated to embodied intelligence. As a top-tier video model, LingBot-Video is designed to bridge the gap between video synthesis and physical world understanding.

关键特性：🚀 Efficient MoE Architecture: Scaled from scratch; balanced between capacity and cost with ~3x faster inference.；**📦 Dat…

项目简介：A skill that turn any brand into a scrollable 3D world

技术栈：JavaScript

核心介绍：An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that builds an immersive, scroll-scrubbed “fly through the world” landing page for any industry or brand — the kind where, as you scroll, a camera flies from *outside* each scene *into* its interior, then flows on to the next scene with no cuts. One continuous connected flight through a little generated world (think the Emons logistics site, applied to whatever you want).

项目数据：⭐ 602 Stars，🍴 54 Forks

技术栈：HTML

核心介绍：این ریپازیتوری، پنل Heimdall (نسخه‌ی بهبودیافته‌ی 3x-ui از sh7CBAC) را به همراه یک nginx reverse proxy اجرا می‌کند که پنل، ساب‌اسکریپشن و اینباند VLESS/WebSocket را از طریق یک پورت واحد (همان پورتی که Railway اختصاص می‌دهد) در دسترس می‌گذارد — دقیقاً همون معماری که برای x4gKing/3x-ui-Upgrade ساختیم و تست شد.

项目数据：⭐ 593 Stars，🍴 1,172 Forks

项目简介：归藏的材质插画 skill：生成带字解释图、图表美化和参考辅助配图。

技术栈：agent、chart-visualization、chinese、claude-code、codex、data-visualization、explainer、illustration

核心介绍：一个适配 Claude Code / Codex 等 Agent 环境的配图 Skill，用来把文章、笔记、图表截图、产品概念、工作汇报、教学材料和人文观点，生成带中文标签的歸藏材质插画。 它解决的是「中间那张图」的问题：社交卡片、PPT、文章和文档里经常需要一张能把意思讲清楚的中心配图，而不是一张漂亮但看不懂的装饰图。 这个 Skill 专注做三件事： > 这是 guizang-social-card-skill 的配套项目。Social Card Skill 负责整张卡片的标题、正文、主题色和尺寸；这个 Skill 负责卡片里的中心插画。 npx skills add https://github.com/op7418/guizang-material-illustration –skill guizang-material-illustration 也可以直接把这段话发给有 shell 权限的 AI Agent：

项目数据：⭐ 524 St…

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the …

We introduce PAST-TIDE, our stance detection system addressing both subtasks of the StanceNakba Shared Task at NakbaNLP@LREC-COLING 2026. The main idea is statement tuning. We redefine stance as cloze-style masked language modeling (MLM), letting a verbalizer map label words to stance categories through the pre-trained MLM head rather than appending a randomly initialized classification head. We complement this with prototypical contrastive learning, which uses learnable class prototypes for batch-size independent contrastive training, and topic-conditional layer normalization for cross-top…

Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each individual object, resulting in reduced frame rates (FPS) with unbounded latency as target count increases. Built upon Segment Anything 2 (SAM2), we propose SAM-MT, which addresses this by transforming the model into an interactive framework for real-time Multi-Target video segmentation. SAM-MT uses ex…

In a class of quantum circuits known as peaked circuits, the goal is to predict the most probable bit string at the output of the circuit. Since these circuits are designed to have a sharp peak in their output distribution, in principle it should be possible to simulate them using a truncated state vector with a limited number of terms, or a fraction of the total probability mass. This approximate simulation can be carried out on a classical computer with a sparse representation that stores only the nonzero amplitudes of the state vector, in contrast to the dense representations that are co…

Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context. This paper presents a comparative study of softmax attention and four recent recurrent linear-attention architectures: DeltaNet, Gated DeltaNet, Kimi Delta Attention, and Gated DeltaNet-2. We express these mechanisms in a common recurrent-memory notation, making explicit how they differ in expressivity, memory decay, erase and write control, training throughput, and implementation complexity. Our experiments center on 350M-parame…

Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influence of disease context on target behavior and therapeutic outcomes. To address this gap, we introduce DrugGen-2, a novel generative model that designs small molecules conditioned on both disease ontology and target protein sequences. DrugGen-2 was developed by fine-tuning a pre-trained GPT-2 model on a curated dataset of approved drugs linked to their diseases and targets, using a two-step strategy of supervised …