Clone Deterministic 3D Worlds with Geometrically-Regularized World Models
"表示学习" 相关文章
HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series
DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation
ICML 2025 | 神经网络何时学到世界模型？清华团队提出通用数学定义
Manifold Approximation leads to Robust Kernel Alignment
Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
Graph Representation Learning with Diffusion Generative Models
Simple and Efficient Heterogeneous Temporal Graph Neural Network
NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation
NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation
MotionBeat: Motion-Aligned Music Representation via Embodied Contrastive Learning and Bar-Equivariant Contact-Aware Encoding
NeurIPS 2025 Spotlight | 条件表征学习：一步对齐表征与准则
Deep SPI: Safe Policy Improvement via World Models
Topological Alignment of Shared Vision-Language Embedding Space
Topological Alignment of Shared Vision-Language Embedding Space
Beyond AlphaEarth: Toward Human-Centered Spatial Representation via POI-Guided Contrastive Learning
马毅团队重磅发布新书：从MCR²到白盒Transformer，重构深度学习的第一性原理
马毅团队重磅发布新书：从MCR²到白盒Transformer，重构深度学习的第一性原理
马毅团队重磅发布新书：从MCR²到白盒Transformer，重构深度学习的第一性原理
马毅团队重磅发布新书：从MCR²到白盒Transformer，重构深度学习的第一性原理
