303 citations · 612 across the 62 of their papers we have counts for
4 papers · 1 filter
TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
Tong Guan, Zijie Meng, Dianqi Li +7
Recent advances in multimodal time series learning underscore a paradigm shift from analytics centered on basic patterns toward advanced time series understanding and reasoning. Ho…
Joint Tensor-Train Parameterization for Efficient and Expressive Low-Rank Adaptation
Jun Qi, Chen-Yu Liu, Sabato Marco Siniscalchi +2
Low-Rank Adaptation (LoRA) is widely recognized for its parameter-efficient fine-tuning of large-scale neural models. However, standard LoRA independently optimizes low-rank matric…
Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
Jun Qi, Jun Du, Sabato Marco Siniscalchi +2
In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expecte…
Maximum a Posteriori Adaptation of Network Parameters in Deep Models
Zhen Huang, Sabato Marco Siniscalchi, I-Fan Chen +2
We present a Bayesian approach to adapting parameters of a well-trained context-dependent, deep-neural-network, hidden Markov model (CD-DNN-HMM) to improve automatic speech recogni…