Zobrazeno 1 - 10
of 735
pro vyhledávání: '"Park, JunYoung"'
Autor:
Berto, Federico, Hua, Chuanbo, Luttmann, Laurin, Son, Jiwoo, Park, Junyoung, Ahn, Kyuree, Kwon, Changhyun, Xie, Lin, Park, Jinkyoo
Multi-agent combinatorial optimization problems such as routing and scheduling have great practical relevance but present challenges due to their NP-hard combinatorial nature, hard constraints on the number of possible agents, and hard-to-optimize ob
Externí odkaz:
http://arxiv.org/abs/2409.03811
Drawing tests like the Rey Complex Figure Test (RCFT) are widely used to assess cognitive functions such as visuospatial skills and memory, making them valuable tools for detecting mild cognitive impairment (MCI). Despite their utility, existing pred
Externí odkaz:
http://arxiv.org/abs/2409.02883
The attention mechanism in text generation is memory-bounded due to its sequential characteristics. Therefore, off-chip memory accesses should be minimized for faster execution. Although previous methods addressed this by pruning unimportant tokens,
Externí odkaz:
http://arxiv.org/abs/2407.15131
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and efficiency. Most SFOD methods
Externí odkaz:
http://arxiv.org/abs/2407.13524
We present a Floquet framework for controlling topological features of a one-dimensional optical lattice system with dual-mode resonant driving, in which both the amplitude and phase of the lattice potential are modulated simultaneously. We investiga
Externí odkaz:
http://arxiv.org/abs/2405.09834
Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of speculative
Externí odkaz:
http://arxiv.org/abs/2404.08856
Text generation with Large Language Models (LLMs) is known to be memory bound due to the combination of their auto-regressive nature, huge parameter counts, and limited memory bandwidths, often resulting in low token rates. Speculative decoding has b
Externí odkaz:
http://arxiv.org/abs/2403.00858
Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this method by
Externí odkaz:
http://arxiv.org/abs/2402.14160
Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment. However, the real-world scenario of continuously changing target distributions presen
Externí odkaz:
http://arxiv.org/abs/2311.05858
When vehicle routing decisions are intertwined with higher-level decisions, the resulting optimization problems pose significant challenges for computation. Examples are the multi-depot vehicle routing problem (MDVRP), where customers are assigned to
Externí odkaz:
http://arxiv.org/abs/2310.14157