TongyiLab · 11 records

dateidtitleauthorsvenue↑
2026-11-112611.12411PhysOPSD: Code as Privilege for Physically Plausible Video GenerationHarold Haodong Chen et al.arXiv8
2026-10-272610.33169World-in-Context: Interactive Video World Modeling with In-Context ConditioningHarold Haodong Chen et al.arXiv32
2026-08-252608.23565ReWorld: An Interactive World Model with Long-Horizon MemoryZhifei Chen et al.arXiv25
2026-07-312607.28227Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI AgentsHanzhang Zhou et al.arXiv107
2026-06-302606.26938Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoEHaoyou Deng et al.arXiv4
2026-06-232606.20002Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement LearningYanxi Chen et al.arXiv11
2026-06-112606.03108EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement LearningGuhong Chen et al.arXiv12
2026-06-022605.29860ESPO: Early-Stopping Proximal Policy OptimizationZihang Li et al.arXiv17
2026-05-252605.18018See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object UnderstandingBoyuan Sun et al.arXiv13
2026-05-202605.20183MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video GenerationYujie Wei et al.arXiv12
2026-05-132605.12481ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use AgentsXuhao Hu et al.arXiv25