Krea's Video Swap Replaces People, Outfits, and Backgrounds in One Shot
Krea's new Video Swap lets creators replace people, outfits, products, or settings in existing clips while preserving motion, camera moves, and sound.
20 stories
Krea's new Video Swap lets creators replace people, outfits, products, or settings in existing clips while preserving motion, camera moves, and sound.
A three-sensor neural network trained on simulation data reconstructs the full temperature and flow fields of a real natural circulation nuclear test rig.
Anthropic launches linked billing in beta, letting customers approve third-party platforms like Linear, Factory, and Ramp without handing over API keys.
OpenAI drops GPT-6.2 Astra and Sol into ChatGPT Work, Codex, and the API, promising frontier results at a third the cost per task.
Goodfire's unsupervised method finds thousands of tiny neuron groups inside Llama-3.1-8B, often under ten neurons, that are causally necessary and sufficient for behaviors like grammar, arithmetic, and formatting.
Midjourney's Edit model now accepts Moodboards, Style Codes, and Style References as drop-in style inputs, no text prompt required.
You.com's new Extract API fetches and parses any URL in one call. On PDFs, it recovers tables, charts, forms and scans that rival extraction APIs largely miss.
Google's new agent mode runs on Gemini 4 Hydrogen, makes phone calls, checks out with Google Pay, and goes free across six countries.
Cognition's new Devin Bots act as managers that direct fleets of coding agents, with beta testers pushing up to 2,000 PRs weekly.
Inferact and Red Hat released a new DSpark draft model for Kimi K3.1 Pro. It gets up to 30% more draft tokens accepted than the preview, and its draft memory stays capped even at 1M-token context.
Parallel launches an image search API built for agents, combining keyword queries with natural-language objectives, starting at $1 per 1,000 requests.
SoduWork is an open-source, self-hosted workbench that runs multiple coding agents side by side with built-in review, governance and plugin sharing.
Perplexity's new Multiagent effort level in Computer uses a lead agent to coordinate a mixed team of frontier models, beating single-model runs on Terminal-Bench 4.1 and WANDR.
Vals AI tested whether frontier models would help pick targets from drone and satellite imagery. Most complied, and a one-line game framing broke the rest.
Spark-X2.6-4B ships as a GGUF-ready on-device agent model with controllable thinking budgets and claims parity with 9B competitors.
IFM drops a 134-page manual on training six open models up to 375B parameters, with new attention tricks and a diffusion decoder that cuts latency up to 2.2x.
Adaption's new plugin lets Nous Research's Hermes Agent generate datasets and fine-tune custom models directly from its own command loop using AutoScientist.
A pixel-space diffusion transformer from CMU and Rice learns to merge related image patches by itself. It scores 1.48 FID on ImageNet and needs 2.4× less training compute than JiT to reach the same quality.
Suno adds AI video generation to its music platform, letting paid users turn songs into lyric clips and music videos with lip sync
Nanonets-OCR2-3B is a compact vision-language model that turns messy documents into clean, LLM-ready markdown with semantic tags for tables, equations, signatures, and more.