arXiv:2604.24602v1 Announce Type: new
Abstract: Vision-language models transfer well in zero-shot settings, but at deployment the visual and textual branches often shift asymmetrically. Under this condition, entropy-based test-time adaptation can shar…
arXiv:2604.24602v1 Announce Type: new
Abstract: Vision-language models transfer well in zero-shot settings, but at deployment the visual and textual branches often shift asymmetrically. Under this condition, entropy-based test-time adaptation can shar…
arXiv:2604.24602v1 Announce Type: new
Abstract: Vision-language models transfer well in zero-shot settings, but at deployment the visual and textual branches often shift asymmetrically. Under this condition, entropy-based test-time adaptation can shar…