Latest in AI and developer tools

Today's trail

updated 14m ago

Pulse · bloomberg.com

bloomberg.com · Nov 13

DeepX Bets $100 Million on New AI Chip Using Samsung Technology

South Korean startup DeepX Co. plans to spend more than $100 million developing a next-generation artificial intelligence chip using Samsung Electronics Co.'s advanced 2 nanometer manufacturing process. DeepX has finished the design of the DX-M2 and sent ...

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/

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Sep 18

Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo-Labelling for Multilingual Dysarthric Speech

Most multilingual dysarthria-severity systems either train on a single aetiology-language pair or pool heterogeneous aetiologies into one label space. We test that pooling assumption with four matched HuBERT-base contrastive embedding models under a shared backbone, training…

arXiv

Sep 18

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subtasks. Collecting additional full-task demonstrations for supervised fine-tuning (SFT) requires operators to repeat behaviors the policy already performs well.…

arXiv

Sep 18

PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection

AI Efficient point-based 3D object detection with Local Attentive Mamba.

arXiv

Sep 18

XCalib Depth-Guided Geometric Optimization for Dense Thermal-Visible Video Registration

Image registration is a vital preprocessing step in multimodal perception tasks, including image fusion, object detection, and semantic segmentation. In Advanced Driver- Assistance Systems (ADAS), spatial misalignment between visible (RGB) and infrared (IR) cameras -caused by…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

This week in Multimodal

Most active this week

Rising tools