Research Papers
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...
ActionSplice Lets Interactive World Models Swap Actions Mid-Generation
A new inference framework, ActionSplice, splices revised actions into chunk-autoregressive video world models without replaying co...
Hugging Face Paper: Agents Can Study New Environments Without a Syllabus
A new Hugging Face paper formalizes task-agnostic environment preprocessing, showing that a meta-agent can explore an unfamiliar e...
New Framework Routes Prompts to LLM Experts as a Bandit Problem
A Hugging Face paper formulates adaptive prompt routing to LLM experts as a contextual bandit problem with limited feedback, propo...
Pelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence
Hugging Face paper introduces Pelican-Sim 1.0, a world model simulator that predicts future observations from visual context and r...
Hugging Face Paper Proposes Diversity-Aware Skill Routing for LLM Agents
A new paper introduces Diverse Skill Routing (DSR), a reranking framework that uses a Determinantal Point Process to balance relev...
Hugging Face Releases Occamy-1.0, a 35B Co-work Agent Model Built for Cost Efficiency
Occamy-1.0 is a cost-efficient co-work agent model derived from the post-trained Qwen3.6-35B-A3B checkpoint, positioned at the low...