Hi-SSLVLM combines hierarchical self-captioning, internal sub-prompt planning, and a CLIP-based consistency loss, and reports judged compositional fidelity gains of roughly 0.04 to 0.09 points that no significance testing or released artifacts support.
Diffusion models beat gans on image synthesis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
Hi-SSLVLM combines hierarchical self-captioning, internal sub-prompt planning, and a CLIP-based consistency loss, and reports judged compositional fidelity gains of roughly 0.04 to 0.09 points that no significance testing or released artifacts support.