Multimodal conversational recommender systems (CRS) integrate dialogue, knowledge graphs, and visual signals. Recent work reports substantial gains over the knowledge-graph baseline KGSF on the INSPIRED dataset (R@10: 0.132→0.257). However, this pipeline couples ViT-based image embeddings with zero-fill handling for 23...
S. Park, Hui-Ling Piao, Jeongtae Lee et al.· Proceedings of the 35th ACM...· 0 citations
This work proposes PrefillShare, a novel algorithm that enables sharing the prefill stage across multiple fine-tuned models in a disaggregated setting and introduces a routing mechanism that enables effective prefill sharing in a vLLM-based disaggregated system.
Sunghyeon Woo, Hoseung Kim, S. Shim et al.· arXiv.org· 3 citations
Carryover Drafting is introduced, a parallel draft--verify--draft training that exposes the drafter to inference-aligned rejected states while preserving parallelism across training positions.
Jahyun Koo, Sunghyeon Woo, J. Kil et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.