Related papers: Liquid Networks with Mixture Density Heads for Eff…
Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…
In this study, we have explored an application of deep learning architecture of the U-Net model, originally designed for biomedical image segmentation, in a regression analysis aimed at predicting fluid flows through textured microchannels.…
Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world applications, such as…
To reduce the computational and memory overhead of Large Language Models, various approaches have been proposed. These include a) Mixture of Experts (MoEs), where token routing affects compute balance; b) gradual pruning of model…
Imitation Learning (IL) has proven highly effective for robotic and control tasks where manually designing reward functions or explicit controllers is infeasible. However, standard IL methods implicitly assume that the environment dynamics…
Discrete diffusion models are increasingly competitive for language modeling, yet it remains unclear how their denoising objectives organize learning. Although these objectives target the full data distribution, we show that the exact…
Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient…
This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared representation between modalities; this can cause poor…
Recently, computational modeling has shifted towards the use of deep learning, and other data-driven modeling frameworks. Although this shift in modeling holds promise in many applications like design optimization and real-time control by…
Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a "meta-policy" from previously learned policies. This paper reports results from experiments using Deep Reinforcement…
Diffusion policies (DP) have demonstrated significant potential in visual navigation by capturing diverse multi-modal trajectory distributions. However, standard imitation learning (IL), which most DP methods rely on for training, often…
Although diffusion models have achieved strong results in decision-making tasks, their slow inference speed remains a key limitation. While consistency models offer a potential solution, existing applications to decision-making either…
Machine learning interatomic potentials (MLIPs) are an emerging modeling technique that promises to provide electronic structure theory accuracy for a fraction of its cost, however, the transferability of MLIPs is a largely unknown factor.…
We present efficient deep learning techniques for approximating flow and transport equations for both single phase and two-phase flow problems. The proposed methods take advantages of the sparsity structures in the underlying discrete…
Score-based generative models like the diffusion model have been testified to be effective in modeling multi-modal data from image generation to reinforcement learning (RL). However, the inference process of diffusion model can be slow,…
Approaches to machine intelligence based on brain models have stressed the use of neural networks for generalization. Here we propose the use of a hybrid neural network architecture that uses two kind of neural networks simultaneously: (i)…
Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data…
Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…
Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, they rely on computationally expensive Reinforcement Learning…
Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes. One such challenge is plasticity loss, wherein a neural network trained in an online fashion…