OrangeBot.AI Digest — 2025-07-20

Improve your resumes with Resume Matcher. Get insights, keyword suggestions and tune your resumes to job descriptions.

Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

The most comprehensive authentication framework for TypeScript

A list of semi to fully remote-friendly companies (jobs) in tech.

The personal finance app for everyone

Sim Studio is an open-source AI agent workflow builder. Sim Studio's interface is a lightweight, intuitive way to quickly build and deploy LLMs that connect with your favorite tools.

We write your reusable computer vision tools. 💜

PlayStation 4 emulator for Windows, Linux and macOS written in C++

Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

Lightweight Firebase/Supabase alternative built to run anywhere — incl. Next.js, Remix, Astro, Cloudflare, Bun, Node, AWS Lambda & more.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Dapr, Rancher Desktop, and Kubernetes.

The Magic Mask for Android

Create sharable checklists with just your voice & AI

AI for Stock & Market Analysis

Split inbox tabs for Gmail. 100% private. 100% free

Free SEO check for Google's E-E-A-T content guidelines

Fresh take on group spaces with friends.

Anonymous messaging via Bluetooth mesh networks by Dorsey

Own the right to invest in the next breakout startup

A new home for your software binaries

Viral LinkedIn posts in your voice

Make a 3D Bust from a single photo, ready for 3D printing

The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational components and the sophisticated implementations that integrate them into intelligent systems. We first examine the foundational components: context retrieval and generation, context processing and context management. We then explore how these components are architecturally integrated to create sophisticated system implementations: retrieval-augmented generation (RAG), memory systems and tool-integrated reasoning, and multi-agent systems. Through this systematic analysis of over 1300 research papers, our survey not only establishes a technical roadmap for the field but also reveals a critical research gap: a fundamental asymmetry exists between model capabilities. While current models, augmented by advanced context engineering, demonstrate remarkable proficiency in understanding complex contexts, they exhibit pronounced limitations in generating equally sophisticated, long-form outputs. Addressing this gap is a defining priority for future research. Ultimately, this survey provides a unified framework for both researchers and engineers advancing context-aware AI.

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not require such an extensive number of visual tokens. While the performance drops significantly in a small subset of OCR-related tasks, models still perform accurately in most other general VQA tasks with only 1/4 resolution. Therefore, we propose to dynamically process distinct samples with different resolutions, and present a new paradigm for visual token compression, namely, VisionThink. It starts with a downsampled image and smartly decides whether it is sufficient for problem solving. Otherwise, the model could output a special token to request the higher-resolution image. Compared to existing Efficient VLM methods that compress tokens using fixed pruning ratios or thresholds, VisionThink autonomously decides whether to compress tokens case by case. As a result, it demonstrates strong fine-grained visual understanding capability on OCR-related tasks, and meanwhile saves substantial visual tokens on simpler tasks. We adopt reinforcement learning and propose the LLM-as-Judge strategy to successfully apply RL to general VQA tasks. Moreover, we carefully design a reward function and penalty mechanism to achieve a stable and reasonable image resize call ratio. Extensive experiments demonstrate the superiority, efficiency, and effectiveness of our method. Our code is available at https://github.com/dvlab-research/VisionThink.

We introduce pi^3, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. Previous methods often anchor their reconstructions to a designated viewpoint, an inductive bias that can lead to instability and failures if the reference is suboptimal. In contrast, pi^3 employs a fully permutation-equivariant architecture to predict affine-invariant camera poses and scale-invariant local point maps without any reference frames. This design makes our model inherently robust to input ordering and highly scalable. These advantages enable our simple and bias-free approach to achieve state-of-the-art performance on a wide range of tasks, including camera pose estimation, monocular/video depth estimation, and dense point map reconstruction. Code and models are publicly available.

This paper addresses the challenge of high-fidelity view synthesis of humans with sparse-view videos as input. Previous methods solve the issue of insufficient observation by leveraging 4D diffusion models to generate videos at novel viewpoints. However, the generated videos from these models often lack spatio-temporal consistency, thus degrading view synthesis quality. In this paper, we propose a novel sliding iterative denoising process to enhance the spatio-temporal consistency of the 4D diffusion model. Specifically, we define a latent grid in which each latent encodes the image, camera pose, and human pose for a certain viewpoint and timestamp, then alternately denoising the latent grid along spatial and temporal dimensions with a sliding window, and finally decode the videos at target viewpoints from the corresponding denoised latents. Through the iterative sliding, information flows sufficiently across the latent grid, allowing the diffusion model to obtain a large receptive field and thus enhance the 4D consistency of the output, while making the GPU memory consumption affordable. The experiments on the DNA-Rendering and ActorsHQ datasets demonstrate that our method is able to synthesize high-quality and consistent novel-view videos and significantly outperforms the existing approaches. See our project page for interactive demos and video results: https://diffuman4d.github.io/ .

Length generalization, the ability to solve problems of longer sequences than those observed during training, poses a core challenge of Transformer-based large language models (LLM). Although existing studies have predominantly focused on data-driven approaches for arithmetic operations and symbolic manipulation tasks, these approaches tend to be task-specific with limited overall performance. To pursue a more general solution, this paper focuses on a broader case of reasoning problems that are computable, i.e., problems that algorithms can solve, thus can be solved by the Turing Machine. From this perspective, this paper proposes Turing MAchine Imitation Learning (TAIL) to improve the length generalization ability of LLMs. TAIL synthesizes chain-of-thoughts (CoT) data that imitate the execution process of a Turing Machine by computer programs, which linearly expands the reasoning steps into atomic states to alleviate shortcut learning and explicit memory fetch mechanism to reduce the difficulties of dynamic and long-range data access in elementary operations. To validate the reliability and universality of TAIL, we construct a challenging synthetic dataset covering 8 classes of algorithms and 18 tasks. Without bells and whistles, TAIL significantly improves the length generalization ability as well as the performance of Qwen2.5-7B on various tasks using only synthetic data, surpassing previous methods and DeepSeek-R1. The experimental results reveal that the key concepts in the Turing Machine, instead of the thinking styles, are indispensable for TAIL for length generalization, through which the model exhibits read-and-write behaviors consistent with the properties of the Turing Machine in their attention layers. This work provides a promising direction for future research in the learning of LLM reasoning from synthetic data.

Controllable captioning is essential for precise multimodal alignment and instruction following, yet existing models often lack fine-grained control and reliable evaluation protocols. To address this gap, we present the AnyCap Project, an integrated solution spanning model, dataset, and evaluation. We introduce AnyCapModel (ACM), a lightweight plug-and-play framework that enhances the controllability of existing foundation models for omni-modal captioning without retraining the base model. ACM reuses the original captions from base models while incorporating user instructions and modality features to generate improved captions. To remedy the data scarcity in controllable multimodal captioning, we build AnyCapDataset (ACD), covering three modalities, 28 user-instruction types, and 300\,k high-quality data entries. We further propose AnyCapEval, a new benchmark that provides more reliable evaluation metrics for controllable captioning by decoupling content accuracy and stylistic fidelity. ACM markedly improves caption quality across a diverse set of base models on AnyCapEval. Notably, ACM-8B raises GPT-4o\'s content scores by 45\% and style scores by 12\%, and it also achieves substantial gains on widely used benchmarks such as MIA-Bench and VidCapBench.

Low-Rank Adaptation (LoRA) has become a widely adopted standard for parameter-efficient fine-tuning of large language models (LLMs), significantly reducing memory and computational demands. However, challenges remain, including finding optimal initialization strategies or mitigating overparametrization in low-rank matrix factorization. In this work, we propose a novel approach that addresses both of the challenges simultaneously within a unified framework. Our method treats a set of fixed-rank LoRA matrices as a smooth manifold. Considering adapters as elements on this manifold removes overparametrization, while determining the direction of the fastest loss decrease along the manifold provides initialization. Special care is taken to obtain numerically stable and computationally efficient implementation of our method, using best practices from numerical linear algebra and Riemannian optimization. Experimental results on LLM and diffusion model architectures demonstrate that RiemannLoRA consistently improves both convergence speed and final performance over standard LoRA and its state-of-the-art modifications.

Spatial reasoning in 3D space is central to human cognition and indispensable for embodied tasks such as navigation and manipulation. However, state-of-the-art vision-language models (VLMs) struggle frequently with tasks as simple as anticipating how a scene will look after an egocentric motion: they perceive 2D images but lack an internal model of 3D dynamics. We therefore propose MindJourney, a test-time scaling framework that grants a VLM with this missing capability by coupling it to a controllable world model based on video diffusion. The VLM iteratively sketches a concise camera trajectory, while the world model synthesizes the corresponding view at each step. The VLM then reasons over this multi-view evidence gathered during the interactive exploration. Without any fine-tuning, our MindJourney achieves over an average 8% performance boost on the representative spatial reasoning benchmark SAT, showing that pairing VLMs with world models for test-time scaling offers a simple, plug-and-play route to robust 3D reasoning. Meanwhile, our method also improves upon the test-time inference VLMs trained through reinforcement learning, which demonstrates the potential of our method that utilizes world models for test-time scaling.

We present Voxtral Mini and Voxtral Small, two multimodal audio chat models. Voxtral is trained to comprehend both spoken audio and text documents, achieving state-of-the-art performance across a diverse range of audio benchmarks, while preserving strong text capabilities. Voxtral Small outperforms a number of closed-source models, while being small enough to run locally. A 32K context window enables the model to handle audio files up to 40 minutes in duration and long multi-turn conversations. We also contribute three benchmarks for evaluating speech understanding models on knowledge and trivia. Both Voxtral models are released under Apache 2.0 license.

Producing expressive facial animations from static images is a challenging task. Prior methods relying on explicit geometric priors (e.g., facial landmarks or 3DMM) often suffer from artifacts in cross reenactment and struggle to capture subtle emotions. Furthermore, existing approaches lack support for multi-character animation, as driving features from different individuals frequently interfere with one another, complicating the task. To address these challenges, we propose FantasyPortrait, a diffusion transformer based framework capable of generating high-fidelity and emotion-rich animations for both single- and multi-character scenarios. Our method introduces an expression-augmented learning strategy that utilizes implicit representations to capture identity-agnostic facial dynamics, enhancing the model's ability to render fine-grained emotions. For multi-character control, we design a masked cross-attention mechanism that ensures independent yet coordinated expression generation, effectively preventing feature interference. To advance research in this area, we propose the Multi-Expr dataset and ExprBench, which are specifically designed datasets and benchmarks for training and evaluating multi-character portrait animations. Extensive experiments demonstrate that FantasyPortrait significantly outperforms state-of-the-art methods in both quantitative metrics and qualitative evaluations, excelling particularly in challenging cross reenactment and multi-character contexts. Our project page is https://fantasy-amap.github.io/fantasy-portrait/.

We introduce AbGen, the first benchmark designed to evaluate the capabilities of LLMs in designing ablation studies for scientific research. AbGen consists of 1,500 expert-annotated examples derived from 807 NLP papers. In this benchmark, LLMs are tasked with generating detailed ablation study designs for a specified module or process based on the given research context. Our evaluation of leading LLMs, such as DeepSeek-R1-0528 and o4-mini, highlights a significant performance gap between these models and human experts in terms of the importance, faithfulness, and soundness of the ablation study designs. Moreover, we demonstrate that current automated evaluation methods are not reliable for our task, as they show a significant discrepancy when compared to human assessment. To better investigate this, we develop AbGen-Eval, a meta-evaluation benchmark designed to assess the reliability of commonly used automated evaluation systems in measuring LLM performance on our task. We investigate various LLM-as-Judge systems on AbGen-Eval, providing insights for future research on developing more effective and reliable LLM-based evaluation systems for complex scientific tasks.

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper introduces a residual learning approach that addresses this feature blindness without requiring complete retraining. We propose training a secondary SAE specifically to model the reconstruction error of a pretrained SAE on domain-specific texts, effectively capturing features missed by the primary model. By summing the outputs of both models during inference, we demonstrate significant improvements in both LLM cross-entropy and explained variance metrics across multiple specialized domains. Our experiments show that this method efficiently incorporates new domain knowledge into existing SAEs while maintaining their performance on general tasks. This approach enables researchers to selectively enhance SAE interpretability for specific domains of interest, opening new possibilities for targeted mechanistic interpretability of LLMs.

Language models (LMs) are challenging to adapt to new data distributions by simple finetuning. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to inefficient tokenization, causing overfragmentation of out-of-distribution domains, unseen languages, or scripts. In this work, we develop byte-level LMs with learnable tokenizers to make tokenization adaptive. Our models include a submodule that learns to predict boundaries between the input byte sequence, encoding it into variable-length segments. Existing tokenizer-free methods train this boundary predictor using an auxiliary loss that enforces a fixed compression rate across the training corpus, introducing a new kind of rigidity. We propose FLEXITOKENS, a simplified training objective that enables significantly greater flexibility during adaptation. Evaluating across multiple multilingual benchmarks, morphologically diverse tasks, and domains, we demonstrate that FLEXITOKENS consistently reduces token over-fragmentation and achieves up to 10\% improvements on downstream task performance compared to subword and other gradient-based tokenizers. Code and data for our experiments will be released at https://github.com/owos/flexitokens

We introduce Einstein Fields, a neural representation that is designed to compress computationally intensive four-dimensional numerical relativity simulations into compact implicit neural network weights. By modeling the metric, which is the core tensor field of general relativity, Einstein Fields enable the derivation of physical quantities via automatic differentiation. However, unlike conventional neural fields (e.g., signed distance, occupancy, or radiance fields), Einstein Fields are Neural Tensor Fields with the key difference that when encoding the spacetime geometry of general relativity into neural field representations, dynamics emerge naturally as a byproduct. Einstein Fields show remarkable potential, including continuum modeling of 4D spacetime, mesh-agnosticity, storage efficiency, derivative accuracy, and ease of use. We address these challenges across several canonical test beds of general relativity and release an open source JAX-based library, paving the way for more scalable and expressive approaches to numerical relativity. Code is made available at https://github.com/AndreiB137/EinFields

Video Frame Interpolation (VFI) aims to predict the intermediate frame I_n (we use n to denote time in videos to avoid notation overload with the timestep t in diffusion models) based on two consecutive neighboring frames I_0 and I_1. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion models are unable to extract temporal information and are relatively inefficient compared to non-diffusion methods. Video-based diffusion models can extract temporal information, but they are too large in terms of training scale, model size, and inference time. To mitigate the above issues, we propose Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation (TLB-VFI), an efficient video-based diffusion model. By extracting rich temporal information from video inputs through our proposed 3D-wavelet gating and temporal-aware autoencoder, our method achieves 20% improvement in FID on the most challenging datasets over recent SOTA of image-based diffusion models. Meanwhile, due to the existence of rich temporal information, our method achieves strong performance while having 3times fewer parameters. Such a parameter reduction results in 2.3x speed up. By incorporating optical flow guidance, our method requires 9000x less training data and achieves over 20x fewer parameters than video-based diffusion models. Codes and results are available at our project page: https://zonglinl.github.io/tlbvfi_page.

最近大规模裁员和重组的芯片巨头突然宣布终止对 Clear Linux 发行版的支持，从即日起不再为 Clear Linux OS 提供安全补丁、更新或维护，项目托管在 GitHub 上的代码库将转为只读模式，它建议使用 Clear Linux 的用户尽快迁移到其它活跃维护的发行版。英特尔在声明中同时强调会继续投资 Linux 生态系统，积极支持和贡献开源项目和 Linux 发行版，支持和优化英特尔硬件。英特尔是在 2015 年为解决容器安全问题而宣布了 Clear Linux 发行版项目，至今有十年历史。

YouTube 主播 Jon Prosser 自今年 1 月起发布了多则视频，展示了苹果要到 6 月份的 WWDC 开发者大会上才公开的 iOS 26 设计细节。此事引起了苹果的注意，它正式对 Prosser 和 Michael Ramacciotti 提起诉讼，指控他们盗窃商业机密。事件的核心是 Ramacciotti 的朋友、苹果员工（已解雇）Ethan Lipnik。Lipnik 持有一部开发中的 iPhone 手机，Prosser 和 Ramacciotti 被控密谋获取这部手机，他们首先窃取密码，然后使用位置追踪技术判断他何时长时间离家。Prosser 向 Ramacciotti 提供经济补偿，Ramacciotti 在 Lipnik 离家后进入其公寓取到了这部开发版 iPhone，通过 FaceTime 向 Prosser 介绍了开发中的 iOS 26。Lipnik 因为未能遵守公司保护开发中和未发布设备和软件的政策而被解雇。苹果不清楚 Prosser 和 Ramacciotti 掌握了多少商业机密，它提起诉讼是为了防止更多机密泄漏。

美国研究人员招募了数百名狗主人收集狗与电视互动的方式。研究考察了狗看电视习惯的趋势，包括主人是否尝试教狗看电视，主人电视每周打开的平均小时数，以及狗关注电视的平均秒数。对狗的评估内容包括它们对动物刺激物、非动物刺激物的反应，以及追随屏幕上的物体的程度。研究发现狗更容易对屏幕上看见的动物而不是其他刺激物作出反应，约 45% 的狗总是能对狗叫和狗吠这类狗噪声作出反应。主人报告为易兴奋的狗被发现会更频繁地追随屏幕上的物体，就好像这些物体存在于现实世界中一样。易害怕或焦虑的狗更容易对汽车喇叭或门铃这类非动物刺激物有反应。调查的狗看电视的平均时长为 14 分 8 秒。

上个月美国联邦法官裁决 Anthropic 使用书籍训练 AI 是合理使用，但使用盗版书籍训练并不是。法庭文件显示，Anthropic 从盗版网站下载了逾 700 万本书籍。它还购买了数百万本纸质书，拆开装订扫描了每一页，将其以数字形式存储。现在对于使用盗版书籍训练大模型，加州地区法官 William Alsup 允许起诉 Anthropic 侵权的作家代表全美作家提起集体诉讼。Anthropic 从盗版电子书库 LibGen 和 PiLiMi 下载了多达 700 万电子书，在 2021 年和 2022 年创建了一个巨大的存储库。如果作家们胜诉，Anthropic 可能需要赔偿数十亿美元损失。

Google 起诉了 25 名僵尸网络 BadBox 2.0 的中国籍运营者。Google 在起诉书中称，截至 2025 年 4 月，BadBox 2.0 感染了全世界逾 1000 万台基于 Android AOSP 系统的设备，包括电视盒、平板、投影仪和车载休闲娱乐系统。BadBox 2.0 是迄今为止发现的规模最大的联网电视僵尸网络。Google 称 BadBox 2.0 的活动干扰了 Google 与客户的关系，损害其声誉，破坏其产品和服务的价值。由于所有被告都在中国，而中美之间很少引渡嫌疑人，因此诉讼不太可能追究到任何被告的责任。

俄罗斯进一步收紧了对网络活动的控制。该国新通过的法律将对搜索被禁止内容以及使用 VPN 访问被禁止内容的人处以罚款。俄罗斯对被禁止内容的定义是一个由政府维护的列表，大约有 5500 个条目，其内容涵盖了从 LGBT运动 到基地等极端主义组织制作的内容，以及宣传纳粹意识形态或或煽动极端主义行为的材料。对搜索被禁止内容的罚款大约为 65 美元，对推广 VPN 等规避审查工具的罚款——个人为 2500 美元，企业最高 1.28 万美元。

新闻出版商行业协会 The News/Media Alliance 宣布成功关闭了帮助用户绕过付费墙的服务 12ft.io。12ft.io 的托管商在该组织的施压下于 7 月 14 日下线了网站。12ft.io 全称 12 Foot Ladder，通过将用户的浏览器伪装成 Web 爬虫从而不受限制的访问网站内容，避开广告、跟踪程序以及弹出式窗口。12ft.io 是由软件工程师 Thomas Millar 在新冠疫情期间创建的，他当时发现 Google 搜索结果前 10 中有 8 个设置了付费墙。12ft.io 下线了，但类似的自托管工具 13 Feet Ladder 允许用户创建无数的 12ft.io。

Mozilla 开发者宣布，预计 7 月 22 日释出的 Firefox 141 将支持 WebGPU。目前对 WebGPU 的支持仅限于 Windows 版本的 Firefox，未来几个月将支持 Linux 和 Mac 版本。WebGPU 为 Web 提供了下一代高性能图形 API，允许在 GPU 上执行渲染和计算操作，Google Chrome 最早于 2023 年引入了对该 API 的支持，而苹果的 Safari 预计将在秋天释出的 v26 中支持 WebGPU。Firefox 的 WebGPU 实现是基于用 Rust 开发的 WGPU，为底层平台的底层图形 API如 Direct3D 12、Metal 和 Vulkan 提供了统一可移植的接口。WGPU 托管在 GitHub 上，是作为一个独立开源项目开发的，Mozilla 是其主要贡献者。

经济学人报道，癌症预防工作取得了成效，自 1990 年代以来发达国家癌症死亡率普遍下降。美国的癌症死亡率自 1990 年代以来下降了约三分之一。发达国家吸烟率下降，仅美国自 1975 年以来就减少了逾 300 万例癌症死亡。英国于 2008 年启动了针对年轻女孩的 HPV 疫苗接种计划，在 15 年内让 20 多岁女性的宫颈癌发病率降低了 90%。治疗方法的进步也改变了部分癌症的治疗结果。曾经致命的儿童白血病，如今五年生存率已超过九成。然而癌症研究的未来面临重重障碍，其中之一是美国特朗普政府计划削减癌症研究经费，中国预计在 2025 年超过美国成为癌症研究的主要资助国。

一项新研究披露，一种基于全球安卓智能手机的地震检测和预警系统能够实时检测地震活动并发出可拯救生命的预警，其效用堪比传统的地震监测网络。许多地震多发国家缺乏地震预警基础设施。智能手机在全球的广泛使用为感测和发送地震警报创建了强大的平台。虽然智能手机中的传感器不如传统地震监测台站的传感器精确，但它们仍然能在强震期间感测地面的震动。安卓地震预警（AEA）功能以默认方式内置于安卓手机，该手机约占全球智能手机用户中的 7 成。在运行的头 3 年（2021-2024 年）中，该 AEA 系统在 98 个国家中平均每月可检测到 312 次地震，震级范围在 1.9 级到最高的 7.8 级之间。对于震级在 4.5 级或以上的地震，该系统向用户发出的警报每月约为 60 次，总计 1800 万次。AES 用户的反馈显示，85% 的警报接收者感受到了地震，其中 36% 是在地面震动开始前收到警报的，28% 是在震动期间收到警报的，23% 则是在震动之后收到警报的。研究人员认为其效用可与已建立的地震监测系统媲美。

Netflix 正式开始着手制作《刺客信条》真人剧集，双方是在约五年前商谈合作。真人剧集的主创和执行制作人为 Roberto Patino 和 David Wiener。Roberto Patino 此前制作了 HBO Max 迷你剧《DMZ》，担任过 Robert De Niro 主演剧集《Zero Day》的编剧和联合执行制作人，参与了《Westworld》和《Sons of Anarchy》等剧集。David Wiener 担任过《Halo》第二季以及《Brave New World》的制作人，为《Fear the Walking Dead》和《Homecoming》写过剧本。Ubisoft Film & Television 的 Gerard Guillemot、Margaret Boykin 和 Austin Dill 也将担任联合制作人。《刺客信条》系列是最畅销的游戏系列之一，2007 年至今共售出逾 2.3 亿份拷贝，主线作品已推出 14 部，最新一部是今年初发布的以日本为背景的《刺客信条：影》。真人剧集的剧情将围绕两个神秘派系的秘密战争展开，一派试图通过控制和操纵决定人类的未来，另一派则致力于维护自由意志。