Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
OmniKVQuant: KV Cache Quantization for Omni-LLMs
Suho Yoo, Hyunjong Ok, Jongmin Choi +2
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-onl…
cs.CV2025
Understanding the Effects of Distractors on Reasoning Vision-Language Models
Jiyun Bae, Hyunjong Ok, Sangwoo Mo +1
How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distra…
cs.CV2025
TempCore: Are Video QA Benchmarks Temporally Grounded?
Hyunjong Ok, Jaeho Lee
Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current Video QA benchmarks genuinely require t…