Výsledky vyhledávání

Report

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning

Autor: Kim, Seyeon, Lee, Joonhun, Cho, Namhoon, Han, Sungjun, Hwang, Wooseop

Conventional uncertainty-aware temporal difference (TD) learning methods often rely on simplistic assumptions, typically including a zero-mean Gaussian distribution for TD errors. Such oversimplification can lead to inaccurate error representations a

Externí odkaz: http://arxiv.org/abs/2408.02295

Zobrazit plný text záznamu

Report

LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs

Autor: Kim, Taeho, Wang, Yanming, Chaturvedi, Vatshank, Gupta, Lokesh, Kim, Seyeon, Kwon, Yongin, Ha, Sangtae

Fine-tuning pre-trained large language models (LLMs) with limited hardware presents challenges due to GPU memory constraints. Various distributed fine-tuning methods have been proposed to alleviate memory constraints on GPU. However, determining the

Externí odkaz: http://arxiv.org/abs/2404.10933

Zobrazit plný text záznamu

Report

MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation

Autor: Kim, Seyeon, Jin, Siyoon, Park, Jihye, Kim, Kihong, Kim, Jiyoung, Nam, Jisu, Kim, Seungryong

Conventional GAN-based models for talking head generation often suffer from limited quality and unstable training. Recent approaches based on diffusion models aimed to address these limitations and improve fidelity. However, they still face challenge

Externí odkaz: http://arxiv.org/abs/2403.19144

Zobrazit plný text záznamu

Report

Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation

Autor: Kim, Kihong, Lee, Haneol, Park, Jihye, Kim, Seyeon, Lee, Kwanghee, Kim, Seungryong, Yoo, Jaejun

Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown comparable performance by compressin

Externí odkaz: http://arxiv.org/abs/2402.13729

Zobrazit plný text záznamu

Report

Diffusion Model for Dense Matching

Autor: Nam, Jisu, Lee, Gyuseong, Kim, Sunwoo, Kim, Hyeonsu, Cho, Hyoungwon, Kim, Seyeon, Kim, Seungryong

The objective for establishing dense correspondence between paired images consists of two terms: a data term and a prior term. While conventional techniques focused on defining hand-designed prior terms, which are difficult to formulate, recent appro

Externí odkaz: http://arxiv.org/abs/2305.19094

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání