Zobrazeno 1 - 10
of 536
pro vyhledávání: '"Keutzer, Kurt"'
Autor:
Yang, Huanrui, Huang, Yafeng, Dong, Zhen, Gudovskiy, Denis A, Okuno, Tomoyuki, Nakata, Yohei, Du, Yuan, Keutzer, Kurt, Zhang, Shanghang
The impact of quantization on the overall performance of deep learning models is a well-studied problem. However, understanding and mitigating its effects on a more fine-grained level is still lacking, especially for harder tasks such as object detec
Externí odkaz:
http://arxiv.org/abs/2407.03442
In this paper, we point out suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixture of all images at every point in
Externí odkaz:
http://arxiv.org/abs/2406.12303
Motion planning in complex scenarios is the core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to plan the future trajectory. Recent methods seek the knowledge preserved in large language mode
Externí odkaz:
http://arxiv.org/abs/2406.07296
Autor:
Huang, Nan, Wei, Xiaobao, Zheng, Wenzhao, An, Pengju, Lu, Ming, Zhan, Wei, Tomizuka, Masayoshi, Keutzer, Kurt, Zhang, Shanghang
Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving. Despite the efficacy of Neural Radiance Fields (NeRF) for driving scenes, 3D Gaussian Splatting (3DGS) emerges as a
Externí odkaz:
http://arxiv.org/abs/2405.20323
Autor:
Liang, Feng, Kodaira, Akio, Xu, Chenfeng, Tomizuka, Masayoshi, Keutzer, Kurt, Marculescu, Diana
This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to process limited frames, we opt to process frames in a streaming fashion
Externí odkaz:
http://arxiv.org/abs/2405.15757
Autor:
Liu, Yijiang, Zhang, Rongyu, Yang, Huanrui, Keutzer, Kurt, Du, Yuan, Du, Li, Zhang, Shanghang
Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications, ranging from content generation to interactive entertainment, and artistic creation. However, the diversity of downstream ta
Externí odkaz:
http://arxiv.org/abs/2404.08985
Autor:
Tan, Sijun, Li, Xiuyu, Patil, Shishir, Wu, Ziyang, Zhang, Tianjun, Keutzer, Kurt, Gonzalez, Joseph E., Popa, Raluca Ada
Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose a novel approach to
Externí odkaz:
http://arxiv.org/abs/2404.07979
Autor:
Lee, Nicholas, Wattanawong, Thanakul, Kim, Sehoon, Mangalam, Karttikeya, Shen, Sheng, Anumanchipali, Gopala, Mahoney, Michael W., Keutzer, Kurt, Gholami, Amir
Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of performance, many
Externí odkaz:
http://arxiv.org/abs/2403.15042
The availability of unprecedented unsupervised training data, along with neural scaling laws, has resulted in an unprecedented surge in model size and compute requirements for serving/training LLMs. However, the main performance bottleneck is increas
Externí odkaz:
http://arxiv.org/abs/2403.14123
Autor:
Hu, Qitian Jason, Bieker, Jacob, Li, Xiuyu, Jiang, Nan, Keigwin, Benjamin, Ranganath, Gaurav, Keutzer, Kurt, Upadhyay, Shriyash Kaustubh
As the range of applications for Large Language Models (LLMs) continues to grow, the demand for effective serving solutions becomes increasingly critical. Despite the versatility of LLMs, no single model can optimally address all tasks and applicatio
Externí odkaz:
http://arxiv.org/abs/2403.12031