HuggingFace
GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods
With the increasing development of Vision-Language Models, it becomes imperative that their predictions are readily e...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
PhysiFormer: Learning to Simulate Mechanics in World Space
We present PhysiFormer, a diffusion transformer for physically-plausible 3D object motion. Unlike video world models ...
HuggingFace
DanceOPD: On-Policy Generative Field Distillation
Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), loca...
HuggingFace
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are o...
HuggingFace
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
While generative AI has achieved remarkable success in solving problems with verifiable solutions, generating physica...
HuggingFace
Fast LeWorldModel
Joint-Embedding Predictive Architectures (JEPAs), including recent LeWorldModel (LeWM), have become a promising found...
HuggingFace
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse traj...
HuggingFace
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
A unified representation for text and vision is a natural pursuit, as it enables simpler multimodal modeling and more...
HuggingFace
Confidence-Aware Tool Orchestration for Robust Video Understanding
Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we t...
HuggingFace
In-Context World Modeling for Robotic Control
Modern Vision-Language-Action (VLA) models often fail to generalize to novel setups, such as altered camera viewpoint...
HuggingFace
OpenBioRQ: Unsolved Biomedical Research Questions for Agents
A working citation looks like proof -- but the fact that a link resolves does not mean the cited paper supports the c...
HuggingFace
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL...