An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmation, call one or several tools, escalate, or refuse. Holding one 27B Korean enterprise model fixed, we vary whether the decision is a generated JSON object or a single...
HyoJung Han, Ryan Kang, Youngeun Kim et al.· 0 citations
Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based token generation. However, their growing model sizes and high inference costs make efficient deployment challenging: full-sequence denoising repeatedly invokes compute-i...
Donghyun Lee, Arkapravo Ghosh, Varun Manjunath et al.· 0 citations
This work introduces ThunderSyncRL, which starts gradient computation as soon as all required inputs are fixed, without policy staleness, and proves that gradient streaming produces the same GRPO and OPD updates as batch-synchronous training, without changing either objective.
Seil Kang, Hangoo Kang, T. Suresh et al.· 0 citations
ALoDLM is introduced, which replaces uniform computation with token-adaptive latent recurrence, and retains fast parallel decoding, yielding a strong quality-efficiency trade-off among evaluated autoregressive and diffusion models under optimized inference engines.
Lian-Cheng Fang, Zhuo-Wei Li, Youngeun Kim et al.· 1 citation
ReaLVR is proposed, which brings visual-evidence supervision to the model's own free-running latent trajectories, and is the first to scale visual reasoning in latent space, showing that the framework continues to deliver robust improvements at frontier model scales up to 235B.
Xi Xiao, Tian-Chen Zhao, Youngeun Kim et al.· arXiv.org· 2 citations
ForGE is proposed, a unified framework for adapting frozen models through per-query routing over a joint action space that spans both support form and thinking depth and improves accuracy at 42-45% lower token cost on both main hosts.
Xi Xiao, Yun-Bei Zhang, Chen Liu et al.· 0 citations
Task-specific fine-tuning on SkillRet improves NDCG@10 by 12.9 points over the strongest prior retriever and by 16.2 points over the strongest off-the-shelf retriever, establishing SkillRet as a strong benchmark and foundation for future research on retrieval in large-scale agent systems.
H. Cho, Ryan Kang, Youngeun Kim· arXiv.org· 40 citations· ⚡7
This work proposes A-PACK, a two-stage framework that defers audio pruning until query-conditioned multimodal interactions emerge inside the LLM, and shows that audio exhibits higher task-relevant information density and representational diversity per token than video.
Kyeong-Jae Lee, Hongyeob Kim, Youngeun Kim et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.