Zobrazeno 1 - 10
of 648
pro vyhledávání: '"Li Tianhong"'
Autor:
Fan, Lijie, Li, Tianhong, Qin, Siyang, Li, Yuanzhen, Sun, Chen, Rubinstein, Michael, Sun, Deqing, He, Kaiming, Tian, Yonglong
Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether models use di
Externí odkaz:
http://arxiv.org/abs/2410.13863
Conventional wisdom holds that autoregressive models for image generation are typically accompanied by vector-quantized tokens. We observe that while a discrete-valued space can facilitate representing a categorical distribution, it is not a necessit
Externí odkaz:
http://arxiv.org/abs/2406.11838
Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale unlabeled data. In
Externí odkaz:
http://arxiv.org/abs/2312.03701
Autor:
Li, Tianhong, Bhardwaj, Sangnie, Tian, Yonglong, Zhang, Han, Barber, Jarred, Katabi, Dina, Lajoie, Guillaume, Chang, Huiwen, Krishnan, Dilip
Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. However, automatically collecting such data (e.g. via large-scale web scraping) leads to low
Externí odkaz:
http://arxiv.org/abs/2310.03734
Autor:
Li, Tianhong, Sivaraman, Vibhaalakshmi, Karimi, Pantea, Fan, Lijie, Alizadeh, Mohammad, Katabi, Dina
Packet loss during video conferencing often results in poor quality and video freezing. Retransmitting lost packets is often impractical due to the need for real-time playback, and using Forward Error Correction (FEC) for packet recovery is challengi
Externí odkaz:
http://arxiv.org/abs/2305.14135
We are concerned with global finite-energy solutions of the three-dimensional compressible Euler-Poisson equations with gravitational potential and general pressure law, especially including the constitutive equation of white dwarf stars. We construc
Externí odkaz:
http://arxiv.org/abs/2305.12615
Generative modeling and representation learning are two key tasks in computer vision. However, these models are typically trained independently, which ignores the potential for each task to help the other, and leads to training and model maintenance
Externí odkaz:
http://arxiv.org/abs/2211.09117
There is a growing literature demonstrating the feasibility of using Radio Frequency (RF) signals to enable key computer vision tasks in the presence of occlusions and poor lighting. It leverages that RF signals traverse walls and occlusions to deliv
Externí odkaz:
http://arxiv.org/abs/2207.02370
Autor:
Xi, Haojun, Li, Tianhong
Publikováno v:
In Science of the Total Environment 1 December 2024 954
Autor:
Li, Tianhong, Cao, Peng, Yuan, Yuan, Fan, Lijie, Yang, Yuzhe, Feris, Rogerio, Indyk, Piotr, Katabi, Dina
Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have investigated the pot
Externí odkaz:
http://arxiv.org/abs/2111.13998