collaborators

10 papers

cs.LG2026

ReOrder-OPD:Reliability-Aware Prompt Ordering for On-Policy Distillation

Ximo Zhu, Ruiqi Liu, Rong Wang +8

On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Existing methods use local conf…

cs.AI2026

Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation

Kaichen Zhang, Wei Huang, Keming Wu +2

Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duplex: new observations cannot n…

cs.CV2026

Visual-Advantage On-Policy Distillation for Vision-Language Models

Ruiqi Liu, Xiaolei Lv, Gengsheng Li +8

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-p…

cs.CV2026

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

Zuhao Yang, Kaichen Zhang, Sudong Wang +7

Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video unders…

cs.AI2026

Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems

Zhiqian Zhang, Xu Zhao, Xiaoqing Xu +5

In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models stil…

cs.SE2025

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging

Ziyi Ni, Huacan Wang, Shuo Zhang +15

Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evalua…