PaDoc: Layout-Grounded Parallel Decoding for Document Parsing Paper • 2608.06146 • Published 6 days ago • 22
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents Paper • 2608.04574 • Published 7 days ago • 14
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 9 days ago • 155
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents Paper • 2608.01827 • Published 9 days ago • 17