XPENG AI · 6 records

dateidtitleauthorsvenue↑
2026-10-142610.16985AUGUstus: Autonomous Driving VLA Model with Unified Generation and UnderstandingYuqi Ye et al.arXiv4
2026-10-132609.39601GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual PrimitivesQize Yu et al.arXiv123
2026-10-132609.39600GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash SpeedQize Yu et al.arXiv47
2026-09-292609.33253VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View SynthesisKangjie Chen et al.arXiv6
2026-09-112609.11412X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale DistillationHaojun Zhang et al.arXiv24
2026-05-202605.18758OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone EnvironmentsFelix Henry et al.arXiv14