HKUSTGZ · 9 records

dateidtitleauthorsvenue↑
2026-11-052611.08373SLA: Scaling Spatial-Language-Action Model via Continual Pre-trainingFuhao Li et al.arXiv82
2026-10-282610.37255Your Policy Is Secretly a Harness: The Decision Geometry of Agent InterfacesJian Mu et al.arXiv8
2026-10-082610.02054UniWAM: Unified World-Action ModelJiayi Chen et al.arXiv77
2026-07-202607.15901DSWorld: A Data Science World Model for Efficient Autonomous AgentsZherui Yang et al.arXiv9
2026-07-132607.04751Trust Region Policy DistillationZhengpeng Xie et al.arXiv34
2026-05-282605.27044BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory ForecastingRuifeng Tan et al.arXiv
2026-05-212605.21131UniT: Unified Geometry Learning with Group Autoregressive TransformerHaotian Wang et al.arXiv7
2026-05-132605.10977PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant AttacksZhenxin Ai et al.arXiv7
2026-05-062604.28123Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RLSudong Wang et al.arXiv46