12 accepted papers
Hardware accelerators such as GPUs, NPUs, and FPGAs are essential to meeting AI’s computational demands. With the proliferation of heterogeneous devices across cloud and edge, various model optimization techniques adapt to diverse hardware characteristics through operator transformations and structu
Concept Bottleneck Models (CBMs) achieve interpretability by interposing a human-understandable concept layer between perception and label prediction. The foundation of CBMs lies in the many-to-many mapping that translates high-dimensional visual features to a set of discrete concepts. However, we…
Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Recent GraphRAG methods introduce structured entity-relation graphs to improve retrieval and reasoning. However, they remain limited by treating knowl
Time series forecasting plays a crucial role in a wide range of real-world applications and has become increasingly complex with the growth of multivariate dimensions and extended historical observations, leading to the prosperity of deep forecasting models. Previous models are hindered by three maj…
Medical diagnosis demands models that can process multimodal medical inputs, such as medical images and patient histories, and generate diverse outputs including textual reports and visual content, such as annotations or segmentation masks. Despite this need, existing medical AI models disrupt this …
This paper proposes Attention-Seeker, an unsupervised keyphrase extraction method that leverages self-attention maps from a Large Language Model to estimate the importance of candidate phrases. Our approach identifies specific components – such as layers, heads, and attention vectors – where the mod…
The Robust Regularized Markov Decision Process (RRMDP) is proposed to learn policies robust to dynamics shifts by adding regularization to the transition dynamics in the value function. Existing methods mostly use unstructured regularization, potentially leading to conservative policies under unreal…
As a recurrent spiking neural network, liquid state machine (LSM) has attracted more and more attention in neuromorphic computing due to its biological plausibility, computation power, and hardware implementation. However, the neural architecture of LSM, such as hidden neuron number, synaptic densit…
We present Matrix Krasulina, an algorithm for online k-PCA, by gen- eralizing the classic Krasulina’s method (Krasulina, 1969) from vector to matrix case. We show, both theoretically and empirically, that the algorithm naturally adapts to data low-rankness and converges exponentially fast to the gro…
Random forests are learning algorithms that build large collections of random trees and make predictions by averaging the individual tree predictions. In this paper, we consider various tree constructions and examine how the choice of parameters affects the generalization error of the resulting rand…
We analyze online (Bottou & Bengio, 1994) and mini-batch (Sculley, 2010) k-means variants. Both scale up the widely used Lloyd’s algorithm via stochastic approximation, and have become popular for large-scale clustering and unsupervised feature learning. We show, for the first time, that they have g…
We provide new analyses of Lloyd’s algorithm (1982), commonly known as the k-means clustering algorithm. Kumar and Kannan (2010) showed that running k-SVD followed by a constant approximation k-means algorithm, and then Lloyd’s algorithm, will correctly cluster nearly all of the dataset with respect…