2026年7月17日 技术热点总结

项目简介：Codex Dream Skin

技术栈：PowerShell

核心介绍：中文 · English 给 Codex 桌面端换一张会呼吸的脸。 外部主题 / 换肤工具 · 本机 CDP 注入 · 不改官方安装包 一张图，一种心情 · 写代码，也要有氛围感 非 OpenAI 官方产品。不修改 .app / app.asar / WindowsApps。 更智能的连接 · 更热爱的创造 热爱驱动 · 无限可能 · Connect AI · Power Creation 感谢 passion8.cc 赞助本项目。 满血 AI 中转：官方模型直连，无降智、无套壳；一行配置接入 Codex / Claude Code / Grok。 换肤与 API 配置互相独立，本项目不会自动改写你的模型供应商设置。 一张图，一种心情。下面都是可落地的主题示意效果： 粉系定制 财神打工版 红白科幻 清透定制 灵感小宇宙 紫夜限定 初音未来 舞台黑金 仓库内按平台放了现成

项目数据：⭐ 5,289 Stars，🍴 619 Forks

项目简介：Your clothes, extracted and organized with gpt-image.

技术栈：JavaScript

核心介绍：Your clothes, extracted and organized with gpt-image. See the original post →

项目数据：⭐ 613 Stars，🍴 83 Forks

Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult. Off-the-shelf compilers can provide useful feedback post-generation, but does not guide intermediate generation steps, such as those during autoregressive LLM decoding. Constrained decoding intervenes earlier by rejecting invalid tokens during sampling, but requires white-box model access and costly reimplementation for semantic constraints.We introduce generative compilation, the first approach to obtaining compiler feedback on partial…

Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even though the models' chains of thought mention the hint much less often. A token-accuracy evaluation would count these runs as successful because they use fewer reasoning tokens with little accuracy loss; it would miss whether the remaining trace still shows what drove the answer. We train Qwen3-4B and Qwen3-14B variants with different target chain le…

Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We address these limitations by introducing SPEAR: A Simulator for Photorealistic Embodied AI Research. At its core, SPEAR is a Python library that can connect to, and programmatically control, any Unreal Engine (UE) application via a modular plugin architecture. SPEAR exposes over 14K unique UE functions to Python, representing an order-of-magnitude increase in progra…

Autonomous UAV systems increasingly rely on multimodal large language models (MLLMs) to operate in complex real-world environments. Such embodied scenarios require not only understanding the surrounding space but also maintaining a coherent representation of the agent itself. However, existing UAV-oriented approaches and benchmarks remain largely environment-centric, primarily focusing on spatial understanding tasks, with the agent's self-awareness remaining implicit. To address this gap, we introduce SIS-Bench, a benchmark for evaluating embodied spatial intelligence in UAV scenarios under…

Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and iterative global refinement capabilities. Unlike continuous diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete diffusion models through the construction of the underlying discrete state …

We present AffectFlow-DINO, a multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a conditional rectified-flow head to model the inherent ambiguity of in-the-wild facial behavior. Instead of predicting a single affect estimate, the model learns a conditional generative distribution, enabling uncertainty-aware one-to-many predictions through Monte Carlo sampling. The system jointly estimates continuous valence-arousal, classifies eight facial expressions, and detects twelve Action Units from static face images. Built on a frozen DINO…