2026年9月12日 技术热点总结

技术栈：PHP

核心介绍：Bank Sampah Digital adalah aplikasi web untuk mengelola bank sampah. Warga bisa menabung sampah, memantau saldo, mengajukan penjemputan, dan mencairkan saldo. Pengelola bisa mencatat setoran, memverifikasi transaksi, dan melihat laporan. Aplikasi ini dibuat mobile-first, jadi nyaman dipakai lewat HP saat petugas berada di lapangan. 1. Warga menyetor sampah yang sudah dipilah. 2. Petugas mencatat jenis, kondisi, dan berat sampah, lalu transaksi disimpan sebagai bukti.

项目数据：⭐ 918 Stars，🍴 0 Forks

核心介绍：中文版 13 Claude Code skills for screenwriting and dramaturgy, distilled from 19 books (Chinese, American and Japanese) plus two complete master-work corpora: Chekhov’s plays and Ozu Yasujiro’s screenplays. Skill bodies are written in Chinese (the sources and quotations are Chinese translations); frontmatter descriptions are in English with Chinese keywords so both languages trigger them.

项目数据：⭐ 743 Stars，🍴 95 Forks

项目简介：Express yourself in meetings (with memes, of course).

技术栈：Python

核心介绍：Pull a face at your webcam. It works out *which* face, and drops the matching meme over your head, scaled to follow you around the frame. You can extend and add more memes to your heart’s desire. Point Zoom at its virtual camera and the whole call sees it. python its_giving.py # preview + virtual camera python its_giving.py –no-vcam # preview only Fourteen reactions: time out, heart hands, hands over face, crashing out,

项目数据：⭐ 713 Stars，🍴 81 Forks

Image tokenizers define the “visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understanding-only evaluations. These evaluations do not fully capture how visual tokens behave when modeled jointly with text. We build a controlled pure-autoregressive testbed and track task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. We examine how these losses scale and relate to downstream performance, then use them to study multimodal learnabilit…

Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work measures rarity primarily through popularity-based metrics such as pageviews. We broaden this view using knowledge-graph structural metrics that capture how well an entity is documented and connected. These metrics identify many rare entities that popularity metrics miss. Across the resulting rare-entity slices, state-of-the-art accuracy drops by 15.4-39.9%, showing that different rarity definitions expose different failure modes. To address …

Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in English regardless of the language they are prompted in. This is inaccessible for non-English-speaking users, risks losing the intent of the original question, and forgoes knowledge more readily expressed in the target language. In this work, we advance L2 reasoning, the ability of a model to reason consistently in the language of the user's prompt, thus building an in-language bridge between the prompt and the answe…

In systems built on Robot Operating System 2 (ROS 2) and using Data Distribution Service (DDS), a single network-impaired or throttled subscriber on a RELIABLE topic can cause backpressure that degrades throughput and latency for all other subscribers, including safety-critical ones sharing the publisher, because the publisher's DDS writer can no longer accept new samples. We present Adaptive Bridge, a proxy-based layer that decouples critical subscribers from degraded or noncritical ones, thereby isolating the critical path through topic splitting and dynamic rate control. The proxy acts a…

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict reference-equivalence to a designated formalization. We formalize this vulnerability as Verdict-Preserving-Unfaithfulness (VPU): a failure mode where an incorrect encoding executes successfully and matches the expected verdict. We theoretically prove that structural, verdict-only verification heuristics are mathematically bounded to chance-level detection on these deceptively valid traces. To resolve this, we introduce Ge…

As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revisions. We study this as Actionable Peer-review Generation and decompose it into two subtasks: diagnostic claim generation and revision suggestion generation. We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans. Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can theref…