Tags
7 pages
Daily Publication
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
Train an LLM to build a multi-agent system
Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
Evaluation bechmark accepted by ICLR
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
Spatial reasoning in VLM using attention visualization
