Research Papers
Harness-Zero Distills Agent Harness Gains Directly Into Model Weights
A new Hugging Face paper proposes Harness-Zero, a method that transfers the benefits of a specialized agent harness into a model's...
Hugging Face Paper Unveils Jev-Mem, a 'System-One' Memory Layer for Faster AI Agents
Jev-Mem splits agentic memory management into a fast System-One control plane and a slower System-Two reasoning plane, reporting b...
Alibaba's Category-Aware Expert Training Boosts SWE Agents to 58% on Pro-618
A new framework from Alibaba trains category-specific software engineering experts via Refresh-Repair-Expand, then consolidates th...
Hugging Face Releases onPanda, a Token-Level Tool That Cuts LLM Annotation Time by 52%
onPanda is an open-source interactive annotation tool that lets humans correct model outputs one token at a time, then resume gene...
D-RAC Brings Retrieval-Aware Chunking to Every Enterprise Document Format
A new Hugging Face paper extends the W-RAC framework into D-RAC, normalizing any document to PDF and converting pages to retrieval...
Grounded Action Models Put 3D Grounding at the Core of Robot Foundation Models
A new Hugging Face paper proposes Grounded Action Models (GAMs), robot foundation models conditioned on language, points, or box p...
Realtime-Venus: Hugging Face Paper Unveils Full-Duplex AI That Talks and Delegates Tasks
A new paper presents Realtime-Venus, a proactive full-duplex interaction system built on two separately trained 9B models that com...
Hugging Face Releases OmniEdu: Open 4B/9B/27B Foundation Models for K-12 Teaching and Learning
OmniEdu is an open family of 4B, 9B, and 27B education foundation models trained on a capability-organized corpus spanning subject...
VideoGen-Agent Trains AI to Orchestrate Video Tools, Boosting Generation Scores by 19 Points
Hugging Face researchers introduce VideoGen-Agent, a multimodal agent trained with multitask agentic reinforcement learning to coo...
Tencent's GameHorizon Suite Offers a New Yardstick for AI Gameplay Skills
A new research suite from Tencent ARC introduces 5,000 hours of annotated AAA gameplay data and a benchmark that evaluates 47 mode...
RoboDawn Lets Vision-Language Models Control Robots Without Task-Specific Training
A new Hugging Face paper introduces RoboDawn, an interface that lets an agentic VLM control a robot through discrete translation,...
WorldCrafter Builds 3D-Aware Memory for Consistent Video World Models
A new video world model, WorldCrafter, learns a camera-queryable implicit 3D-aware memory that keeps long-horizon scene exploratio...