Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights Paper • 2602.01219 • Published Sep 27 • 1
Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few Paper • 2509.16875 • Published Nov 5, 2025 • 1
Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective Paper • 2411.03033 • Published Oct 9, 2025 • 1
FileGram: Grounding Agent Personalization in File-System Behavioral Traces Paper • 2604.04901 • Published Apr 6 • 36
Octopus: Embodied Vision-Language Programmer from Environmental Feedback Paper • 2310.08588 • Published Oct 12, 2023 • 38