output
20042026
most citedAdaBins: Depth Estimation using Adaptive Bins

716 citations

117 papers

cs.AR2026

Hot-Cold Tiering of HBM and High Bandwidth Flash for Agentic LLM Serving

Jongjin Baek, Won Ji, Seungjae Yoo +1

Large language model (LLM) serving is increasingly agentic, with multi-turn sessions that idle between actions yet must retain their full context. Limited GPU memory capacity force…

cs.DB2026

Aker: Density-Aware Approximate Caching for Vector Search (Extended Version)

Sukjoon Oh, Minki Kang, Dohyun Kim +5

Disk-based approximate nearest neighbor search (ANNS) incurs high I/O overhead due to frequent disk accesses during index traversal. Approximate caching, which reuses the results o…

cs.CV2026★ 1 cited

Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images

Jihyun Lee, Hangil Park, Yongmin Seo +4

In this paper, we tackle automatic anomaly detection in multi-illumination and multi-focus display images. The minute defects on the display surface are hard to spot out in RGB ima…

cs.IT2026

Demand-Aware Cooperative Transmission Design for Energy-Efficient LEO Satellite Networks

Wooseok Cha, Kyeongsoo Kim, Seonghoon Kim +2

Low Earth orbit (LEO) satellite networks are envisioned as a promising solution for providing ubiquitous connectivity and narrowing the digital divide. The extensive footprint of L…

cs.CV2026★ 1 cited

Splat-based 3D Scene Reconstruction with Extreme Motion-blur

Hyeonjoong Jang, Dongyoung Choi, Donggun Kim +2

We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur, a frequent challenge in low-light environments. Under dim ill…

cs.CV2026

EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes

Jihyeok Jung, Jeewu Lee, Sanghyeop Kim +2

Existing egocentric benchmarks have primarily constructed the egocentric setting from first-person-view data, which makes it difficult to evaluate egocentric perspective itself in…