Multi-modal sensing has demonstrated remarkable efficacy for intra-site beam prediction. However, generalizing trained models to unseen environments remains a significant challenge, primarily due to the inherent environment-specific wireless propagation characteristics. Existing cross-environment works rely on either r...
Lei Wang, Chang-Yi Li, Kai Dong et al.· IEEE International Symposium...· 0 citations
Large Language Model (LLM) reprogramming-based beam prediction demonstrates strong data efficiency by adapting pretrained language models for vehicle-to-infrastructure (V2I) beam prediction, yet the resulting model complexity makes such approaches impractical for latency-sensitive deployment. We propose LLMBP-Lite, a c...
Kai Dong, Lei Wang, Chang-Yi Li et al.· 0 citations
This work shows that counting ability can be introduced into training-free anomaly detection without additional training or part-level supervision, and proposes a normal-set calibration that aligns heterogeneous anomaly cues using statistics from normal images, enabling their direct fusion within a unified training-fre...
Chang-Yi Li, Miao Yu, Kai-Ling Dong et al.· 0 citations
An adaptive temporal modeling framework for WSVAD that explicitly accounts for variations in video dynamics across multiple temporal granularities is proposed and an adaptive similarity-based fusion strategy that dynamically integrates anomaly scores into video-level predictions is proposed, replacing fixed top-k aggre...
This work proposes audio-first triage: select windows using the lightest modality, scored before any video frame is decoded, so the approach composes naturally with token compression or quantization.
Masoud Jalayer, Chang-Yi Li, Yu Xiao· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
