activity
20212026
most citedMoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models

5 citations · 12 across the 32 of their papers we have counts for

collaborators

38 papers

cs.AI2026

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Hanzhang Zhou, Panrong Tong, Xu Zhang +13

GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate reliably on…

cs.CV2026

UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving

Xiaowei Gao, Pengxiang Li, Yitai Cheng +4

Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off betw…

cs.RO2026

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

Huimin Wang, Yue Wang, Bihao Cui +7

We introduce ReflectDrive-2, a masked discrete diffusion planner with separate action expert for autonomous driving that represents plans as discrete trajectory tokens and generate…

cs.CL2026

StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation

Miaohe Niu, Pengxiang Li, Jingbo Zhu +1

Complex retrieval-augmented generation requires evidence retrieval and control over what to retrieve next, which paths to explore, whether evidence is sufficient, and which interme…

cs.CV2026

Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes

Pengxiang Li, Joey Tsai, Hongwei Xue +2

Diffusion Language Models (DLMs) promise highly parallel text generation, yet their practical inference speed is often bottlenecked by suboptimal decoding schedulers. Standard appr…

cs.CL2026

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Pengxiang Li, Dilxat Muhtar, Tianlong Chen +2

Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-right, autoregressive (AR)-like…