ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context Paper • 2609.36684 • Published 9 days ago • 13
VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering Paper • 2609.19879 • Published 21 days ago • 33
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization Paper • 2609.14320 • Published 25 days ago • 34
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published Sep 4 • 28