Related papers: PRISM: Performer RS-IMLE for Single-pass Multisens…

Large language model (LLM) pruning with fixed N:M structured sparsity significantly limits the expressivity of the sparse model, yielding sub-optimal performance. In contrast, supporting multiple N:M patterns to provide sparse…

Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, data imbalances, and limited text annotations in datasets. Addressing these challenges requires…

Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…

Data collection in imitation learning often requires significant, laborious human supervision, such as numerous demonstrations, and/or frequent environment resets for methods that incorporate reinforcement learning. In this work, we propose…

A wide range of user perception applications leverage inertial measurement unit (IMU) data for online prediction. However, restricted by the non-i.i.d. nature of IMU data collected from mobile devices, most systems work well only in a…

We introduce \prism{} (\textbf{P}robabilistic \textbf{R}etrieval with \textbf{I}nformation-\textbf{S}tratified \textbf{M}emory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. \prism{} unifies…

Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often…

Reinforcement Learning (RL) has made significant strides in complex tasks but struggles in multi-task settings with different embodiments. World model methods offer scalability by learning a simulation of the environment but often rely on…

Rapid progress in imitation learning, foundation models, and large-scale datasets has led to robot manipulation policies that generalize to a wide-range of tasks and environments. However, rigorous evaluation of these policies remains a…

Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic…

Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal. A popular class of approach infers the (unknown) reward function via inverse reinforcement learning (IRL) followed…

Latent state space models are a fundamental and widely used tool for modeling dynamical systems. However, they are difficult to learn from data and learned models often lack performance guarantees on inference tasks such as filtering and…

Multi-sequence Magnetic Resonance Imaging (MRI) offers remarkable versatility, enabling the distinct visualization of different tissue types. Nevertheless, the inherent heterogeneity among MRI sequences poses significant challenges to the…

Precise robot manipulations require rich spatial information in imitation learning. Image-based policies model object positions from fixed cameras, which are sensitive to camera view changes. Policies utilizing 3D point clouds usually…

Behavioral software models play a key role in many software engineering tasks; unfortunately, these models either are not available during software development or, if available, quickly become outdated as implementations evolve. Model…

Scene graphs have emerged as accurate descriptive priors for image generation and manipulation tasks, however, their complexity and diversity of the shapes and relations of objects in data make it challenging to incorporate them into the…

Contact-rich manipulation depends on applying the correct grasp forces throughout the manipulation task, especially when handling fragile or deformable objects. Most existing imitation learning approaches often treat visuotactile feedback…

Multimodal sentiment analysis (MSA) aims to predict human sentiment from textual, acoustic, and visual information in videos. Recent studies improve multimodal fusion by modeling modality interaction and assigning different modality…

Although deep learning-based personalized recommendation systems provide qualified recommendations, they strain data center resources. The main bottleneck is the embedding layer, which is highly memory-intensive due to its sparse, irregular…