Zobrazeno 1 - 10
of 95
pro vyhledávání: '"Kuleshov, Volodymyr"'
Real-world data streams can change unpredictably due to distribution shifts, feedback loops and adversarial actors, which challenges the validity of forecasts. We present a forecasting framework ensuring valid uncertainty estimates regardless of how
Externí odkaz:
http://arxiv.org/abs/2409.19157
Autor:
Sahoo, Subham Sekhar, Arriola, Marianne, Schiff, Yair, Gokaslan, Aaron, Marroquin, Edgar, Chiu, Justin T, Rush, Alexander, Kuleshov, Volodymyr
While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple masked discrete diffusion is mo
Externí odkaz:
http://arxiv.org/abs/2406.07524
Large-scale sequence modeling has sparked rapid advances that now extend into biology and genomics. However, modeling genomic sequences introduces challenges such as the need to model long-range token interactions, the effects of upstream and downstr
Externí odkaz:
http://arxiv.org/abs/2403.03234
Autor:
Schiff, Yair, Wan, Zhong Yi, Parker, Jeffrey B., Hoyer, Stephan, Kuleshov, Volodymyr, Sha, Fei, Zepeda-Núñez, Leonardo
Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics. However, many of these syst
Externí odkaz:
http://arxiv.org/abs/2402.04467
Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing their weights to low-precision. In this work, we introduce QuIP#, a weight-only PTQ method that achieves state-of-the-art results in extreme compression regimes ($\le
Externí odkaz:
http://arxiv.org/abs/2402.04396
We propose denoising diffusion variational inference (DDVI), an approximate inference algorithm for latent variable models which relies on diffusion models as flexible variational posteriors. Specifically, our method introduces an expressive class of
Externí odkaz:
http://arxiv.org/abs/2401.02739
Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images. Central to these algorithms is the diffusion process, a set of equations which maps data to noise in a way that can significantly affect performance. I
Externí odkaz:
http://arxiv.org/abs/2312.13236
Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences. To enable
Externí odkaz:
http://arxiv.org/abs/2312.12009
Publikováno v:
Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence (2024)
Causal discovery is crucial for causal inference in observational studies, as it can enable the identification of valid adjustment sets (VAS) for unbiased effect estimation. However, global causal discovery is notoriously hard in the nonparametric se
Externí odkaz:
http://arxiv.org/abs/2310.17816
Autor:
Gokaslan, Aaron, Cooper, A. Feder, Collins, Jasmine, Seguin, Landan, Jacobson, Austin, Patel, Mihir, Frankle, Jonathan, Stephenson, Cory, Kuleshov, Volodymyr
We assemble a dataset of Creative-Commons-licensed (CC) images, which we use to train a set of open diffusion models that are qualitatively competitive with Stable Diffusion 2 (SD2). This task presents two challenges: (1) high-resolution CC images la
Externí odkaz:
http://arxiv.org/abs/2310.16825