We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) \textbf{Long-to-short Video Evidence Curricu...
Interactive 3D head generation requires coordinated speaking and listening motion that responds to an evolving conversation. Existing generators use incoming observations as context but keep their parameters fixed, leaving conversational patterns unused as a learning signal. We introduce EvolvingAvatar, a causal genera...
Analytical analyses show that learned rubric priorities systematically vary across dialogue stages and user emotions, demonstrating that CARE adapts what is rewarded as support needs evolve.
Peng-Yu Huang, Zhi-Yuan Han, Wen-Wen Tong et al.· 0 citations
MOJITO is proposed, a unified sensor-to-action framework for end-to-end autonomous driving built on modal joint learning that performs block-wise Modal Joint Attention that simultaneously updates action, image, and LiDAR features, allowing the planner to directly access multi-modal features during action generation.
Zhijing Cheng, Xuan Zhang, Donglin Di et al.· arXiv.org· 0 citations
TextGaze is proposed, a unified cross-modal architecture that leverages a Large Vision-Language Model (LVLM) as scalable semantic guidance to balance the two design paradigms and highlight the potential of LVLMs as accessible auxiliary guidance for gaze estimation.
J. She, Fei Wang, Kun Li et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
