HuggingFace
TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models
Large-scale action pretraining equips Embodied Foundation Models (EFMs) with strong manipulation capabilities, with p...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it we...
HuggingFace
What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are c...
HuggingFace
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relation...
HuggingFace
WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we prese...
HuggingFace
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B acti...
HuggingFace
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requir...
HuggingFace
SplatLab: Autonomous Scientific Discovery for 3DGS Research
Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed. Prior auto...
HuggingFace
MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models
Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inferenc...
HuggingFace
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
We present WorldStream, an open-ended 3D world model with three simultaneous capabilities: it extends playable terrai...
HuggingFace
From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a ...
HuggingFace
Retrieval Augmented Generation Compositionality
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine em...