RSDE, Microsoft
3 papers at NeurIPS 2025
We propose GUI-Actor, a VLM-based, coordinate-free GUI grounding method with an attention-based action head and verifier, achieving state-of-the-art results and strong generalization.
RetrievalAttention improves decoding speed and reduces GPU memory usage in Transformer-based LLMs by using pre-built, attention-aware KV vector indexes stored in CPU memory, achieving significant efficiency gains without compromising accuracy.
