Author
Korea Advanced Institute of Science and Technology
We have 4 of 82 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.
Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or undermine trust. This work proposes foundations for designing, realizing, and evaluating proactive LLM agents around three joint principles (3T): Task Capability, anti...
Q-TIE is proposed, a re-ranking framework based on learned Temporal Intent Extraction that generalizes beyond predefined rules via model-based learning while explicitly modeling temporal constraints as a separate signal - jointly achieving what each paradigm typically trades off.
This paper proposes BALIGN, a balanced data selection strategy that explicitly mitigates catastrophic forgetting while optimizing alignment efficacy, and identifies three key data-centric features that dictate parameter drift: the reference model's log-probability margin, the token length between chosen and rejected re...
Flux is proposed, a multimodal federated learning framework built around two complementary components, modality-aware confidence tempering and gradient-decoupled private adaptation, that enables sample-specific, client-local confidence adaptation without allowing confidence-dependent gradients to perturb shared represe...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
