A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds Paper • 2403.04594 • Published Mar 7, 2024
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning Paper • 2504.20073 • Published Apr 24, 2025 • 12
LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World Paper • 2506.00980 • Published Jun 1, 2025
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration? Paper • 2602.07055 • Published 6 days ago • 15
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction Paper • 2511.20937 • Published Nov 26, 2025 • 16
Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models Paper • 2407.01906 • Published Jul 2, 2024 • 46
Re-thinking Temporal Search for Long-Form Video Understanding Paper • 2504.02259 • Published Apr 3, 2025 • 1
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning Paper • 2504.20073 • Published Apr 24, 2025 • 12