Enhancing Multi-Agent Coordination via Dialogue Alignment
Explore how dialogue-driven world model alignment improves multi-agent coordination in AI, reducing conflicts but challenging task success rates.
Optimizing Data Difficulty for LLM Fine-Tuning Success
Discover how data difficulty impacts LLM fine-tuning and the tradeoff between generalization and extrapolation for better model performance.
RISED Framework: Ensuring Safe Clinical AI Deployment
Discover the RISED framework for pre-deployment safety evaluation of clinical AI decision-support systems, enhancing reliability, equity, and performance.
EcoGEO: Enhancing Web Search with Trajectory-Aware LLM Agents
Discover EcoGEO's trajectory-aware evidence ecosystems that optimize web-enabled LLM agents for smarter, more effective online search and information retri...
Orthrus: Fast, Memory-Efficient Parallel Token Generation
Discover Orthrus, a dual-view diffusion framework that boosts token generation speed by 7.8x with minimal memory overhead and high-quality text output.