Junchi Yan
2 papers · Latest:
Robotics
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
GuidedVLA enhances VLA models by specializing action attention heads with auxiliary signals to focus on task-relevant factors, improving generalization and robustness.
2605.12369
Artificial IntelligenceBEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design
BEAM introduces a bi-level, memory-adaptive algorithmic evolution for LLM-powered heuristic design, significantly outperforming existing methods.
2604.12898
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.