SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that PersistsResearchSep 22, 2026
A framework for recipe data structure with applications for culinary and nutritional insightsResearchSep 22, 2026
AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented GenerationResearchSep 22, 2026
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta AttentionResearchSep 22, 2026
AWR-Net: Decoupling Anatomy and Appearance for 3D Fetal Brain Ultrasound SynthesisResearchSep 22, 2026
StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather ForecastingResearchSep 22, 2026
GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language AgentsResearchSep 22, 2026
SolarFlowRefiner: Refinement-Aware Flow Matching for Surface Solar Radiation DownscalingResearchSep 22, 2026