Latest in AI and developer tools

Today's trail

updated 17m ago

Pulse · techjuice.pk

techjuice.pk · Nov 14

OpenAI's New ChatGPT Wallet Brings AI Agents Into Online Shopping

OpenAI launches ChatGPT Wallet, allowing AI agents to make purchases on users' behalf with biometric approval and secure card payments.

Pulse · note.com

note.com · Nov 14

Is it the boss's fault when a subordinate's performance doesn't improve? Is it the same for AI agents and humans?

A subordinate's performance is not improving.In such a case, what should a boss consider?"Is it a lack of ability?" "Is it a lack of effort?" "Is it a lack of motivation?"Of course, there are cases where the cause lies with the subordinate themselves.

Pulse

Top picks this weekarXiv

arXiv

Nov 12

Back to Pixels: Lifting Latent Video Diffusion into Pixel Space

Frontier video generation models work in a VAE latent space that compresses video in both space and time. This compression made training tractable, but now limits high-resolution, controllable, and interactive generation -- doubling resolution quadruples token count, conditions apply to groups of frames rather than individual ones, and each response must wait for the rest of its multi-frame block. We present PixVid, a simple yet effective method that lifts a pretrained latent video model to directly generate every frame in pixel space. PixVid keeps the diffusion transformer and replaces the VAE decoder with a convolutional head that renders its outputs into pixels. We find that predicting clean video rather than velocity, together with a larger noise shift, is key to quality. Finetuned from Wan2.1-14B, PixVid is competitive with the latent baseline within $\sim 1.3$M training clips. Working framewise in pixels, it generates at $2\times$ higher resolution with the same per-frame token count, keeps depth-conditioned video editing aligned under fast motion, and responds to each action at the next frame. Project page: https://chenshuo20.github.io/PixVid/