graphical interfaces, gesture interfaces, multimodal interactions, voice interactions
TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
arxiv.org·3d
"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
arxiv.org·3d
Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment
arxiv.org·2d
Loading...Loading more...