2026年10月2日 技术热点总结

项目简介：AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese

技术栈：Python、agent-skills、ai-writing、antigravity、claude-code、codex、cursor、gemini、japanese

核心介绍：『yomiyasu（よみやす）』は、AIが生成した日本語の不自然さを解消し、人間が読みやすく情報密度の高い日本語へ推敲するためのスキルです。 主に技術記事、設計書・仕様書、PR説明文、社内レポートなどの実務的な文章を対象として設計されています。 Codex、Claude Code、CursorをはじめとするAIコーディング環境に読み込ませて使用してください。 開発背景や言語学的病理の分析、複数のコーパスによる検証結果については、以下の解説記事で詳しく紹介しています。 ALGO ARTISについて > 株式会社 ALGO ARTIS は、私たちが社会基盤の最適化に取り組んでいるスタートアップです。 > 電力・海運・鉄道・化学プラントといった現場では、膨大な制約が絡み合う複雑な運用計画を、今なお熟練者が手作業で組み立てています。 > 弊社では、そうした高度な…

项目简介：Claude Code skill kit for premium AI-assisted business videos: independent critic loop, motion principles from 28 launch films, quality bar, sound design, business offers, Three.js patterns, scripts

技术栈：Python

核心介绍：A Claude Code skill (also usable as plain context for any LLM) for making premium, launch-style commercials for real businesses with AI-generated footage, code-built motion (HTML/GSAP), selective Three.js, and an independent-critic quality loop.

项目数据：⭐ 879 Stars，🍴 72 Forks

项目简介：43 film styles, each a reusable style prompt plus a short film made entirely in code by Claude Opus 5.5. Pick a style, bring your own story, and let your agent direct. | Opus5.5 x 43 种影片风格：风格提示词 + 纯代码样片 + 导演与技术指南

技术栈：JavaScript、ai-agents、ai-video、animation、canvas、claude、claude-code、creative-coding、ffmpeg

核心介绍：Pick a style, bring your own story, and let your coding agent direct the film. 选一个风格，带上你自己的故事，让你的编程 agent 来当导演。 ▶ Watch the gallery · 看图鉴 One Clawd walks through all 98 Best Picture winners, each one redrawn in a style that fits the film. Every frame, every note…

项目简介：Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.

技术栈：JavaScript、2d-animation、ai-agents、ai-video、animation、claude-code、codex、multi-agent、style-transfer

核心介绍：Sugar Rush music video · hand-painted · 58 s Sunshine Boy music video · hand-painted · 63 s Bath Time narrated comic · 30 s Each one made with ReelMimic from a reference video and a one-line brief. Previews are silent, with the lyrics cropped out. Ever watched a video and thought “I want one in that style, but completely my own”? Just …

Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with established vision-language pretraining pipelines. Recent advances in pixel-space modeling offer an encoder-free alternative, but extending this paradigm from images to videos is non-trivial: video understanding and generation adopt different temporal representations, leaving the design of a unified visual interface an open question. We present PixelUMM, an encoder-free model for unified image and video understand…

We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and how it weighs them. The dominant approach, outcome-supervised RL (e.g., GRPO), credits every token in the rollout with a single scalar determined only by the accuracy of the final verdict, providing no separate credit at the criterion-choice tokens and ignoring the rich language feedback (e.g., preference rationales) that naturally accompanies preference labels. Self-Distillation (SD) is one natural way to use this…

One-step generators enable high-quality visual generation with a single network evaluation, but their post-training is difficult: general implicit generators provide neither tractable likelihoods nor denoising trajectories, and many rewards are non-differentiable. We introduce Reward-Weighted Transport Distillation (RWTD), a post-training method that requires only generated samples and scalar reward evaluations. Rather than aligning solely to the conventional reward-tilted reference distribution, RWTD constructs an adaptive target that mixes separately tilted current and reference distribut…

TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but their sequential decoding incurs substantial latency. Non-autoregressive alternatives offer much faster generation, yet often rely on more restrictive reference conditioning, such as requiring transcripts of the reference speech during inference. We present Tacit-TTS, an efficient transcript-free zero-shot voice cloning system distilled from IndexTTS2. Our model replaces autoregressive text-to-semantic decoding with masked non-autoregressive gener…

Reward models score responses from large language models (LLMs) and guide LLM training toward human preferences. However, reward models can favor superficial attributes such as length or confidence, leading LLMs to produce higher-scoring but not more correct responses. Existing mitigation methods either retrain the reward model or apply a fixed correction to one known bias, such as a preference for longer responses. Retraining requires additional data and computational resources, while existing editing methods require the target bias to be specified in advance and use a fixed edit for that …

Artificial-intelligence (AI) agents hold promise for automating bioimage analysis, yet no benchmark evaluates whether they can carry out real-world analyses end to end. Such analyses are hard for agents because 2D images, 3D volumes and time-lapse sequences are often too large to read as context, so an agent must choose and run an analysis through code, specialized software and rendered views. Published studies make this capability testable, because each pairs raw images with a peer-reviewed result. We introduce BIABench, a benchmark of 16 tasks reconstructed from published biological studi…