Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

## Episode Summary In this episode, we cover: - **Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models** (arXiv) - [Read more](http://arxiv.org/abs/2606.27373v1) - **CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies** (Hugging Face Daily) - [Read more](https://huggingface.co/papers/2606.16613) - **PhysiFormer: Learning to Simulate Mechanics in World Space** (arXiv) - [Read more](http://arxiv.org/abs/2606.27364v1) - **RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation** (arXiv) - [Read more](http://arxiv.org/abs/2606.27345v1) - **Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning** (arXiv) - [Read more](http://arxiv.org/abs/2606.27330v1) --- *Sponsored by LimitLess AI*