Rendering document text as images allows vision-language models to encode documents as visual tokens, which can reduce input sequence length compared with text input. This reduction in input length is particularly useful for reranking, where each query involves scoring multiple candidate documents and token savings app...
Seongtae Hong, Youngjoon Jang, Jungseob Lee et al.· 0 citations
Fine-tuning adapts aligned large language models (LLMs) to downstream tasks, but a few dozen harmful examples can remove their refusal of harmful requests. Prior work localizes safety-related behavior to specific layers, directions, and tokens, suggesting targets for protection. We test whether successful localization...
Jungseob Lee, D. Lee, Sugyeong Eo et al.· 1 citation
Knowledge distillation aims to transfer the factual knowledge of large language models to smaller models for efficient deployment. Yet a teacher may recall a relation in one direction while failing to generate the answer in the reverse direction. Distillation from its generated answers can therefore propagate this dire...
Jungseob Lee, Sugyeong Eo, Seongtae Hong et al.· 0 citations
A byte crossover is derived, the context length at which the two savings are equal, together with ideal speedup bounds for each branch and for their composition, from model dimensions and keep ratios alone and is derived at https://github.com/js-lee-AI/ByteCross.
Jungseob Lee, Seungyoon Lee, Seongtae Hong et al.· 1 citation
GLANCE is presented, the first one-pass block drafter that is lossless on an unmodified VLM target, and it breaks the cycle at both ends of a self-defeating cycle.
Jungseob Lee, Seongtae Hong, D. Lee et al.· 0 citations
DART is introduced, a training-free routing framework that samples two cheap no-think drafts, accepts direct answering when the drafts agree, and predicts a thinking budget from draft entropy when they disagree, and preserves or improves always-thinking accuracy in most settings while reducing thinking-token use.
Jungseob Lee, Seongtae Hong, Seungjun Lee et al.· arXiv.org· 1 citation
Funnel of Thoughts (FoT) is introduced, an inference-time method that preserves the full 32-trajectory voted accuracy while halving its attention FLOPs, a 28.8% reduction in full-model inference cost.
Chanhee Park, Sun Han, Jeongho Yoon et al.· 0 citations
This work releases LAMAR, a language aware multilingual cross encoder trained to account for both semantic relevance and language coherence, which achieves the best performance overall and across all languages examined individually on general multilingual reranking benchmarks.
Seongtae Hong, Youngjoon Jang, Jungseob Lee et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
