HuggingFace
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-impro...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation
Language-guided panoramic video generation benefits various downstream applications, such as interactive 3D scene exp...
HuggingFace
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
When a coordinator compares answers from heterogeneous foundation models, self-reported confidence may have different...
HuggingFace
SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery
Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across ex...
HuggingFace
Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
Reinforcement learning (RL) has become a key paradigm for enhancing the reasoning of large language models, yet the h...
HuggingFace
CARE: Certifying Acceleration for Vision-Language-Action Inference
While vision-language-action (VLA) models have advanced rapidly, running them at every control step remains expensive...
HuggingFace
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a ce...
HuggingFace
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth mot...
HuggingFace
WorldGuide: Goal-Directed Video World Model for Procedural Task Execution
Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedur...
HuggingFace
REMORY: Learning Residual Memory for Context Compaction
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may...
HuggingFace
SpaceFlow: Locally Controllable 3D Generation
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control s...
HuggingFace
EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
Sparse GNN training reduces computation, but deciding which edges to keep can be costly. Reusing one sparse graph is ...