SIT-LMPC: Safe Information-Theoretic Learning Model Predictive Control for Iterative Tasks
Publisher ICRA
Year 2026
Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
Publisher ArXiv
Symskill: Symbol and Skill Co-Invention for Data-Efficient and Reactive Long-Horizon Manipulation
Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation
Publisher ICLR
The LU-Mirage – An independent evaluation of the zero-shot claims in the LUMIR challenge
Publisher MIDL
TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
Publisher ICML
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Publisher CVPR
Viability-Preserving Passive Torque Control
Vibe Spaces for Creatively Connecting and Expressing Visual Concepts
When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
