Neuromorphic computing aims to mimic both the function and structure of biological neural networks to provide artificial intelligence with extreme efficiency.
While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation.
4 code implementations • 22 May 2023 • Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Huanqi Cao, Xin Cheng, Michael Chung, Matteo Grella, Kranthi Kiran GV, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartlomiej Koptyra, Hayden Lau, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Xiangru Tang, Bolun Wang, Johan S. Wind, Stansilaw Wozniak, Ruichong Zhang, Zhenyuan Zhang, Qihang Zhao, Peng Zhou, Jian Zhu, Rui-Jie Zhu
We propose a novel model architecture, Receptance Weighted Key Value (RWKV), that combines the efficient parallelizable training of Transformers with the efficient inference of RNNs.
The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting.
We present MEMprop, the adoption of gradient-based learning to train fully memristive spiking neural networks (MSNNs).
We present a fully memristive spiking neural network (MSNN) consisting of physically-realizable memristive neurons and memristive synapses to implement an unsupervised Spiking Time Dependent Plasticity (STDP) learning rule.
The natural spiking dynamics of the MIF neuron model are fully differentiable, eliminating the need for gradient approximations that are prevalent in the spiking neural network literature.
The use of analog resistance states for storing weights in neuromorphic systems is impeded by fabrication imprecision and device stochasticity that limit the precision of synapse weights.
We present the first experimental demonstration of a neuromorphic network with magnetic tunnel junction (MTJ) synapses, which performs image recognition via vector-matrix multiplication.
With the application of artificial intelligence in the financial field, quantitative trading is considered to be profitable.
The net value of the fund is affected by performance and market, and the researchers try to quantify these effects to predict the future net value by establishing different models.
The authors combined the deep Q network in reinforcement learning with the sentiment quantitative indicator ARBR to build a high-frequency stock trading model for the share market.
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses.
Ranked #1 on 3D-Aware Image Synthesis on FFHQ 256 x 256
no code implementations • 16 Mar 2021 • Alexander J. Edwards, Dhritiman Bhattacharya, Peng Zhou, Nathan R. McDonald, Walid Al Misba, Lisa Loomis, Felipe Garcia-Sanchez, Naimul Hassan, Xuan Hu, Md. Fahim Chowdhury, Clare D. Thiem, Jayasimha Atulasimha, Joseph S. Friedman
We therefore propose a reservoir that meets all of these criteria by leveraging the passive interactions of dipole-coupled, frustrated nanomagnets.
This paper studies video inpainting detection, which localizes an inpainted region in a video both spatially and temporally.
The conditional generative adversarial network (cGAN) is a powerful tool of generating high-quality images, but existing approaches mostly suffer unsatisfying performance or the risk of mode collapse.
Ranked #7 on Conditional Image Generation on ImageNet 128x128
To learn the sampling policy, a Markov decision process is embedded into the search algorithm and a moving average is applied for better stability.
Recognizing the expressions of partially occluded faces is a challenging computer vision problem.
In this paper, we target refining the boundaries in high resolution images given low resolution masks.
Reservoir computing is an emerging methodology for neuromorphic computing that is especially well-suited for hardware implementations in size, weight, and power (SWaP) constrained environments.
In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective.
For machines to achieve this capability, we propose a knowledge-enabled language representation model (K-BERT) with knowledge graphs (KGs), in which triples are injected into the sentences as domain knowledge.
Finally, through this easy-to-use specification language, we are able to build a full testing specification which leverages LLVM TableGen to automatically generate unit tests for ONNX operators with much large coverage.
Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots.
The advent of image sharing platforms and the easy availability of advanced photo editing software have resulted in a large quantities of manipulated images being shared on the internet.
On the other hand, in addition to the conventional discriminator of GAN (i. e., to distinguish between REAL/FAKE samples), we propose a novel guider sub-network which encourages the generated sample (i. e., with novel pose) towards better satisfying the ReID loss (i. e., cross-entropy ReID loss, triplet ReID loss).
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned.
Joint extraction of entities and relations is an important task in information extraction.
Ranked #3 on Relation Extraction on NYT-single
To integrate the features on both dimensions of the matrix, this paper explores applying 2D max pooling operation to obtain a fixed-length representation of the text.
Ranked #5 on Text Classification on TREC-6
Ranked #28 on Relation Extraction on SemEval-2010 Task 8