13 citations · 34 across the 8 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation
Daeun Kim, Junwha Hong, Changhun Oh +3
Autoregressive image generation has emerged as a paradigm for multimodal AI systems due to its compatibility with transformer-based LLM serving infrastructures. However, generating…
cs.ET2026
Understanding the Performance Behaviors of End-to-End Protein Design Pipelines on GPUs
Jinwoo Hwang, Yeongmin Hwang, Tadiwos Meaza +2
Recent computational advances enable protein design pipelines to run end-to-end on GPUs, yet their heterogeneous computational behaviors remain undercharacterized at the system lev…