This research presents a framework for adapting the OpenAI Whisper architecture to the unique acoustic and linguistic challenges of the policing environment by employing Parameter-Efficient Fine-Tuning (PEFT) through Low-Rank Adaptation (LoRA), and addresses the significant performance degradation observed in zero-shot...
V. Senthil, Zhiqiang Tao, Ernest Fokoué· arXiv.org· 0 citations
AttnSign is proposed, a VLM-based spatial-temporal attention steering framework for sign language translation that first introduces spatial attention supervision for sign-relevant regions in each frame; then develops an RL-based motion-cadence steering method that encourages the model to explore and focus on sign-level...
Meibo Hu, Guohao Sun, Annemarie D. Ross et al.· 0 citations
This work shows that CFG can be interpreted as isolating the instruction-induced residual in the action space by contrasting conditional and unconditional predictions, thereby explicitly amplifying the effect of the navigation command at inference time, and proposes Latent-Centroid Steering (LCS), a single-pass guidanc...
Meibo Hu, Jiamian Wang, Pichao Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.