Africa
Physics-based Zero-Shot Video Generation Antonio Montanaro
However, it seems that including the dimension of time remains challenging.
Conformalized Time Series with Semantic Features
Conformal prediction is a powerful tool for uncertainty qua ntification, but its application to time-series data is constrained by the violati on of the exchangeability assumption. Current solutions for time-series prediction typically operate in the output space and rely on manually selected weights to addres s distribution drift, leading to overly conservative predictions. To enable dyna mic weight learning in the semantically rich latent space, we introduce a novel a pproach called Con-formalized Time Series with Semantic Features (CT -SSF). CT -SSF utilizes the inductive bias in deep representation learning to dynamica lly adjust weights, prioritizing semantic features relevant to the current predic tion. Theoretically, we show that CT -SSF surpasses previous methods defined in the ou tput space. Experiments on synthetic and benchmark datasets demonstrate tha t CT -SSF significantly outperforms existing state-of-the-art (SOT A) conformal p rediction techniques in terms of prediction efficiency while maintaining a valid cov erage guarantee.
Discrete Modeling via Boundary Conditional Diffusion Processes Y uxuan Gu Xiaocheng Feng Lei Huang Yingsheng Wu Zekun Zhou
We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling.
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs Yue Y u Georgia Tech Wei Ping
Wang et al., 2024) is a widely used technique for customizing large language models (LLMs) to handle
Learning the Latent Causal Structure for Modeling Label Noise
In label-noise learning, the noise transition matrix reveals how an instance transitions from its clean label to its noisy label. Accurately estimating an instance's noise transition matrix is crucial for estimating its clean label.
ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
One notable advantage of using OT in the latter setting is that, compared to other generative approaches, such as GANs, Normalizing Flows, or Diffusion Models, there is no assumption for one of the measures to be defined in a closed form ( e.g., Gaussian or uniform)
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
As Large Language Models (LLMs) are increasingly deployed in specialized domains with continuously evolving knowledge, the need for timely and precise knowledge injection has become essential.