3 papers
cs.LG2026
SAGE: Training-Free Semantic Evidence Composition for Edge-Cloud Inference under Hard Uplink Budgets
Inhyeok Choi, Hyuncheol Park
Edge-cloud hybrid inference offloads difficult inputs to a powerful remote model, but the uplink channel imposes hard per-request constraints on the number of bits that can be tran…
cs.CV2026
Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
Sangjune Park, Inhyeok Choi, Donghyeon Soon +2
Dance is a form of human motion characterized by emotional expression and communication, playing a role in various fields such as music, virtual reality, and content creation. Exis…
cs.LG2026
ASPEN: Spectral-Temporal Fusion for Cross-Subject Brain Decoding
Megan Lee, Seung Ha Hwang, Inhyeok Choi +3
Cross-subject generalization in EEG-based brain-computer interfaces (BCIs) remains challenging due to individual variability in neural signals. We investigate whether spectral repr…