We have 6 of 42 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, however, a user's personal context is much richer, comprising reviews, posts, images, captions, and metadata accumulated over time. A truly personalized g...
Existing Large Language Model (LLM) routing methods score LLMs independently to select top-$k$ models. However, this ignores model correlations and enforces a rigid computational budget. Consequently, routers often select redundant models that share failure modes, limiting the overall probability of success. To address...
SimLoss is proposed, a reference-free embedding-space objective for single-pass fine-grained image captioning, and results show that embedding-space supervision can recover the quality of multi-stage verification at the latency of a single-pass captioner.
Diverse Skill Routing is proposed, a diversity-aware reranking framework that uses a Determinantal Point Process to balance relevance and non-redundancy and improves recall and full coverage over a strong pointwise reranking baseline, with larger gains on multi-skill queries.
SignBALANCE is proposed, whose magnitude is composition-free: it keeps the verifier sign, uses a global scale, and restores zero-mean balance via a stop-gradient per-class rescaling.
The results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
