GUI-SD: On-Policy Self-Distillation for GUI Grounding
Discover GUI-SD, an efficient on-policy self-distillation method enhancing GUI grounding accuracy and training speed for AI agents.
Instance-Aware Parameter Tuning for ECVRP Optimization
Boost Electric Capacitated Vehicle Routing with instance-aware parameter tuning in Bilevel Late Acceptance Hill Climbing for improved routing efficiency.
AI’s Role in Human-Machine Symbiosis Explained
Explore how AI shapes human-machine symbiosis, enhancing collaboration, transparency, and ethical AI use in content creation and beyond.
Interleaved Vision-Language Reasoning for Robot Manipulation
Discover the IVLR framework that combines vision and language for enhanced long-horizon robot manipulation with a 95.5% success rate on LIBERO tasks.
AEM: Boost Multi-Turn RL Agents with Adaptive Entropy
Discover AEM, a supervision-free method enhancing multi-turn RL agents by optimizing exploration-exploitation and improving training efficiency.