As Omni-modal large language models (Omni-LLMs) take in audio, video and text together, their KV cache memory cost grows. KV cache quantization is the de facto approach in text-only LLMs, but its application to Omni-LLMs remains unexplored. In this paper, we analyze how TurboQuant, a representative rotation-based KV ca...
Suho Yoo, Hyunjong Ok, Jongmin Choi et al.· 0 citations
The analyses show how VLM evaluation behaves as model panels grow and evolve, providing guidance for designing future benchmarks that are more efficient, robust to model turnover, and explicit about the limits of evaluation-side pruning.
This work introduces Frame Selection Sensitivity (FSS), a per-sample diagnostic that measures how much VLM accuracy changes when the most relevant frames are replaced with the least relevant ones, and constructs TempCore, compact evaluation subsets that isolate temporal samples from existing benchmarks.
Hyunjong Ok, Jaeho Lee· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.