From the 1 of 6 linked papers with an AI index.
6 papers
Flux-OPD: On-Policy Distillation with Evolving Contexts
Yuran Wang, Zekun Wang, Bohan Zeng +10
The paper introduces Flux-OPD, a method for training large language models by distilling knowledge from teachers while using evolving contexts as supervision, and stabilizes the pr…
WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts
Yuxin Meng, Yuhan Suo, Junjie Wang +9
Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence and miss the requirement-induced states and transitions that determine whether a page…
Video-Zero: Self-Evolution Video Understanding
Ruixu Zhang, Deyi Ji, Lanyun Zhu +4
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains…
SPAN: Continuous Modeling of Suspicion Progression for Temporal Intention Localization
Xinyi Hu, Yuran Wang, Ruixu Zhang +3
Temporal Intention Localization (TIL) is crucial for video surveillance, focusing on identifying varying levels of suspicious intentions to improve security monitoring. However, ex…
Beyond the Individual: Introducing Group Intention Forecasting with SHOT Dataset
Ruixu Zhang, Yuran Wang, Xinyi Hu +5
Intention recognition has traditionally focused on individual intentions, overlooking the complexities of collective intentions in group settings. To address this limitation, we in…
Anomize: Better Open Vocabulary Video Anomaly Detection
Fei Li, Wenxuan Liu, Jingjing Chen +4
Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel…