Latest stories
Study Questions 'Lossless' Claim of Orthrus Speculative Decoding Under BF16
An independent reproduction of the Orthrus speculative-decoding architecture finds exact trajectory matching in only about 45% of...
Hugging Face Paper Unveils LynnReal-Omni, a 32B Multimodal Video Diffusion Framework for Agentic Visual Workflows
LynnReal-Omni is a unified multimodal video diffusion framework that combines agentic visual controls with high-fidelity generatio...
Hugging Face Paper Proposes Grouped Value Attention to Shrink KV Caches
A new paper introduces Grouped Value Attention (GVA), which stores grouped values and reconstructs content keys with a learned lin...
RSIAgent Lets Frozen Models Self-Improve by Scaling Experience, Not Parameters
A new training-free multi-agent framework from Aether Labs builds reusable environment memory through broad-then-deep exploration,...
Hugging Face Paper Proposes 'Discovery Foundation Models' for Open-Ended Scientific Discovery
A new paper argues that the next frontier for foundation models is Discovery Intelligence: participating in how new problems, repr...
PhysBrain 1.5 Turns Vision-Language Models Into Unified Physical Foundation Models
Hugging Face paper introduces PhysBrain 1.5, an 8B model that jointly learns physical understanding, action generation, and future...
ZGCM-1: A Fully Open 7B Model That Thinks, Searches, and Helps Build Itself
ZGCM-1 is a fully open 7B dense foundation model trained from scratch for extreme data, system, and algorithmic efficiency, pairin...
Vidu S2 Brings Real-Time, Editable, Spatial Video Generation to Life
Hugging Face paper introduces Vidu S2, a pair of real-time models for interactive avatars and video editing, with support for 720p...
Atria Dawn Preview: A Foundation Agent Trained on Verified Tool Interactions
Hugging Face paper introduces Atria Dawn Preview, an agentic language model trained through a Verifiable Experience Pipeline, whic...
Dream-RSI Lets AI Agents 'Dream' in Their Own Discovery History to Self-Improve
A new Hugging Face paper introduces Dream-RSI, a framework that turns accumulated discovery history into an offline replay simulat...
Hugging Face Paper: 2B Model Tops EgoLongQA 2026 by Distilling a Tool-Using Agent
A sub-2B vision-language model distilled from the perception module of a tool-using agent placed first in the ≤2B division of the...
Hugging Face Paper: Ambient Tops EgoProactive 2026 With Visually Grounded Wearable AI
Ambient's submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge ranked first in the large-model division and...