Results demonstrate an effective quality--efficiency trade-off for strict one-step text-to-motion generation, and introduce differentiable decoded-space kinematic supervision to complement normalized representation matching with constraints in the decoded motion space.
H. Dinh, B. Mai, Tran Quoc Bao Le et al.· 0 citations
This paper designs a novel backdoor attack mechanism that incorporates multiple types of backdoor trigger, focusing on stealthiness and effectiveness, and proposes reducing the magnitude of each trigger type and combining them to achieve a strong backdoor relying on the combined trigger while still staying safely under...
Duc Anh Vu, Vuong Quoc Anh Pham, Le Hoang Nguyen et al.· IEEE Access· 0 citations
This work introduces SPATIALQUERY, a training- free framework for CIDQ reasoning from a single RGB image, together with SPATIALQUERY-1M, a benchmark containing over one million RGB-only question-answer pairs from 200 indoor scenes, and proposes Uncertainty-Aware Chain-of-Thought (UA-CoT) prompting, which incorporates g...
Hai-Tra Nguyen, Tung Vu, Cong Tran· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.