Research Papers
Hugging Face Unveils Miles v0.1: Open-Source System for Production-Level Post-Training
Miles v0.1 is an open-source, production-ready system for large-scale reinforcement learning and post-training, supporting diverse...
GE-Act 2.0: A From-Scratch World-Action Model for Scalable Zero-Shot Robot Manipulation
Hugging Face researchers introduce GE-Act 2.0, a world-action model trained entirely from scratch on manipulation data, achieving...
DriveZero: End-to-End Autonomous Driving That Goes Beyond Human Demonstrations
Hugging Face researchers introduce DriveZero, an end-to-end autonomous driving system that combines a vision foundation model with...
Hugging Face Unveils Gander: An End-to-End Omni-Modal Agent for Real-Time Interaction
Gander is a new end-to-end framework that integrates continuous multi-modal streaming, real-time full-duplex interaction, and agen...
Hugging Face Researchers Unveil On-Policy Reverse Distillation to Surpass Weak Supervisors
A new paper from Hugging Face introduces On-Policy Reverse Distillation (OPRD), a method that lets stronger AI models learn from w...
Hugging Face Unveils NeoHorse-1: A Step Toward Recursive Self-Improvement in AI Agents
NeoHorse-1, a new family of agent-native models from Hugging Face, uses agentic post-training with intelligent routing and feedbac...
Split-LLM Training Leaks Real Data Through Zero-Gradient Patterns, Study Finds
A systems-security case study shows that a split-LLM training setup passed its privacy checks while the returned gradient revealed...
SimpleMemVLA Drops Dedicated Memory Modules for Raw Video History in Robot Policies
A new vision-language-action model feeds intact, timestamped video history straight into a pretrained VLM backbone, letting hidden...
Hugging Face Paper Proposes Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
A new Hugging Face paper introduces narrow-boundary safety alignment, using self-generated refusal data and harmful-benign boundar...
Hugging Face Researchers Unveil Conformal Relevance Framework for NLP Tasks
A new framework from Hugging Face automates score function design for conformal prediction using in-context learning and ensemblin...
On-Policy Self-Distillation: A Critical Review Maps the Three Levers of Reasoning Collapse
A new critical review examines on-policy self-distillation (OPSD) for mathematical reasoning, framing reasoning collapse as a symp...
EmbodiedSkills: A Unified Framework for Closed-Loop VLA Agents
Hugging Face researchers propose EmbodiedSkills, a framework that verifies robot skill executions via a fixed interface, enabling...