2026年7月18日 技术热点总结

项目简介：Scroll-scrubbed ‘fly through the world’ burger demo, generated with Kubeez. Live: meepcastana.github.io/kubeez-scroll-world-video

技术栈：JavaScript

核心介绍：> A scroll‑scrubbed “fly through the world” landing page. As you scroll, a pre‑rendered > camera glides forward through a miniature clay burger world — market → grill → counter → > the burger — as one continuous shot, no cuts. Every frame was generated with > Kubeez. ▶ Watch the full 20-second video · or scroll the live demo yourself. Scroll doesn’t move a page here — it drives a camera. Each scene is…

项目简介：One-click desktop GUI for the Aether censorship-circumvention tunnel — Tauri v2, React 19, Rust

技术栈：TypeScript、anti-censorship、censorship-circumvention、desktop-app、proxy、react、rust、tauri、typescript

核心介绍：This project does not reimplement any of Aether’s tunneling logic. It drives the real aether binary in a pseudo-terminal, answers its interactive setup prompts on your behalf, and watches its output to tell you what’s happening. All the actual censorship-circumvention work — MASQUE/QUIC obfuscation, WireGuard, route probing — is Aether’s, not this repo’s.

关键特性：**Auto …

项目简介：Open-source macOS AI copilot that floats over your screen, sees/hears your meetings, and stays hidden from screen shares. Cluely alternative, bring-your-own-key.

技术栈：JavaScript

核心介绍：A free, self-hosted alternative to Cluely. Bring your own AI key (OpenAI · Anthropic · Google Gemini). > On Zoom specifically, whether cue is hidden depends on one setting — Settings → Share Screen → Screen capture mode → “Advanced capture with window filtering.” >

项目数据：⭐ 481 Stars，🍴 98 Forks

Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts…

Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to achieve logical consistency and low-latency streaming for complex reasoning tasks. We propose HDR (Hierarchical Denoising for Visual Reasoning), a unified framework that integrates hierarchical latents into causal video generation for multi-step reasoning. HDR o…

Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We introduce Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination. Unlike vision-language models that emphasize scene understanding and textual decision making, or generative world models that mainly predict future visual states, RxBrain represents embodied plans in a single planning sequence where language and visual imagination play complementary roles. Language provides the abstract structure of a plan, including task…

In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and crucially (b) incorporates a new notion of per-token times, with some tokens proceeding from noise to token at a faster rate than others. Continuous space modeling helps TTCD avoid the parallel sampling of multiple tokens, which is a key source of inaccuracy at high speedups for models that iterate purely in discrete space. The notion of per-token times helps TT…

CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models, yet typically their correspondences are appearance-driven and degrade under occlusion or sim-to-real domain shift. To address these limitations, we introduce SUFLECA (Scaling Up Feature LEarning for CAD Alignment), a weakly-supervised framework for zero-shot CAD alignment with two key contributions. First, SUFLECA …

Recent generalizable 3D Gaussian Splatting models have advanced long-sequence novel view synthesis (NVS), but at the cost of substantial redundant computation. We identify that the redundancy can be mitigated based on two observations: (i) high-precision geometry is not strictly required for high-quality NVS; (ii) appearance learning is generally easier than geometry recovery. Motivated by these insights, we propose an asymmetric architecture that decouples geometry and appearance modeling. The geometry branch processes coarse-grained tokens with most of the parameters for multi-view recons…