AI
Training Proactive and Personalized LLM Agents
Researchers propose a new paradigm for training language models (LLMs) to be proactive and personali...
AI
SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation
Researchers have developed SlideGen, a system for generating presentation slides from scientific pap...
AI
VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection
Researchers have developed a new AI system called VSAL that can detect properties of graphs. Graphs ...
AI
Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary
Researchers have identified a problem in multi-agent systems where agents learn from each other's be...
AI
ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation
Researchers have proposed a new benchmark called ATP-Bench for evaluating the ab...
AI
Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints
Researchers have developed a new framework called AWARE that improves the accura...
AI
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
Researchers have developed a method called activation steering to prevent langua...
AI
MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
Researchers have developed a new framework called MAVEN-T for real-time multi-ag...