Havuz

PixelRAG, web sayfaları ve belgeleri screenshot tile’larına dönüştürüp görsel içerik üzerinden arayan bir RAG sistemi sunuyor.

Neden yükseliyor · 121 günde 10.101 yıldıza ulaşması ve 8,28 milyon Wikipedia sayfasını içeren canlı indeks/API sunması dikkat çekiyor. README, Berkeley SkyLab, BAIR ve Berkeley NLP bağlantılı araştırma çalışmasını resmi kod tabanı olarak tanımlıyor. Son 28 günde 5 commit ve 4 farklı yazar görünmesi katkı çeşitliliğine işaret etse de aktiviteyi çok yüksek göstermiyor.

Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. 逆向一切视频，逐个镜头看是拍的、AI 生成的还是代码做的，再告诉你怎么复刻。

TokenSpeed, agentic workloads için LLM inference sunumunu hızlandırmayı ve istek yönetimini daha güvenli hale getirmeyi amaçlayan bir inference engine’dir.

Neden yükseliyor · 144 günde 2.178 yıldız ve son 28 günde 385 commit ile 20 farklı yazar, hem ilgi hem de yakın dönem geliştirme faaliyeti gösteriyor. README ayrıca PyTorch Ecosystem’e katılımı ve yeni model desteğini vurguluyor; performans iddiaları ise proje tarafından sunulan kıyaslamalara dayanıyor.

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted A

A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T

[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

AI 视频解说全流程 skill 包：自动切镜头、看画面写解说词、配音合成成片，支持一键导出可编辑的剪映/CapCut 草稿，无需 GPU ｜ Agent skills that turn videos into narrated recaps & editable CapCut

Boot your PC straight into an LLM. Rust, UEFI-resident, no operating system underneath.

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw

Real-time 3D digital twin of an autonomous warehouse — 20 AMRs, deterministic simulation, explainable fleet scheduling, failure injection, V

Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels in

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-mo

AI-agent skill producing reusable Markdown from PDFs. It turns flowcharts, diagrams, and charts into text beside each caption instead of emp

Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel

[NeurIPS 2026] Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

DR Pixel: Page-Native Deep Research with Vision-Language Models — benchmark, evaluation harness and training code

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

NullFlux — 本地部署的中文 CFD / 科学计算智能体（OpenFOAM · MFIX · LBM · ParaView · 视觉核验 · 论文复现），by LZF

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

Search knowledge by what documents mean and how they look — not one or the other.

Android 16 fork. AI as a platform primitive. Twelve capabilities, one shared runtime, every app. OEM-pluggable. Apache 2.0.

Semark converts PDFs, Office files, HTML, and images into RAG-ready semantic Markdown using MinerU and VLM/LLM review, with chunks, source m

Pure-Rust DWG -> multipage PNG renderer + lossless position-referenced text layer & metadata indexer for RAG/VLM ingestion of CAD drawings