CERES is proposed, a closed-loop multimodal indexing framework that builds a three-level semantic pyramid, mines implicit concepts via a co-occurrence-aware router, performs scale-routed cross-attention into a lightweight U-Net generator, and verifies coverage by re-indexing the generated image with the same frozen VLM.
Guangyuan Dong, Chuang Liu, Hao-Yu Wang et al.· 1 citation
This work identifies the Logit Conflation Problem, where a to-ken’s logit aggregates prompt-independent factors, including linguistic fluency and parametric associations, with prompt-relevance, and proposes SEAL-Sampling to isolate this component through attention-weighted attribution.
Pinlong Zhao, Huijun Tang, Pengfei Jiao et al.· Annual Meeting of the Associ...· 0 citations
This work proposes B-APO (Bias-Targeted Adversarial Preference Optimization), which casts debiasing as a bias-targeted min-max game: it generates hard negatives by applying small adversarial perturbations in the latent space to maximally induce language-vision-prior reliance, and then performs preference alignment to enlarge the margin between clean and adversarial responses.
Pinlong Zhao, Zike Ding, Zengshu Ye et al.· Annual Meeting of the Associ...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
