GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object DetectionResearchSep 30, 2026
VISTA: Internalizing Collective Visual Experience via On-Policy Distillation for Active Multimodal AgentsResearchSep 30, 2026
Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy HistoryResearchSep 30, 2026
VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video AgentsResearchSep 30, 2026
E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPUResearchSep 30, 2026