HuggingFace
On-Policy Delta Distillation
On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constrain...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse lang...
HuggingFace
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, con...
HuggingFace
Qwen-Music Technical Report
In this report, we introduce Qwen-Music, a powerful music generation model capable of producing highly musical and hi...
HuggingFace
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existin...
HuggingFace
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI...
HuggingFace
When Does Muon Help Agentic Reinforcement Learning?
Muon is competitive with AdamW in large-scale pre-training, but its value for reinforcement-learning (RL) post-traini...
HuggingFace
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy c...
HuggingFace
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural know...
HuggingFace
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grad...
HuggingFace
See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models
Vision-language-action (VLA) models predict robot actions from visual observations and language instructions. These a...
HuggingFace
Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies
Autonomous negotiation agents are increasingly deployed in high-stakes settings such as insurance and procurement. Wh...