20 accepted papers
We introduce Hybrid Convolutions with Attention Stochasticity (HyCAS), an adversarial defense that narrows the long-standing gap between provable robustness under ℓ2 certificates and empirical robustness against strong ℓ∞ attacks, while preserving strong generalization across diverse imaging benchma…
Current methods for multivariate time series forecasting can be classified into channel-dependent and channel-independent models. Channel-dependent models learn cross-channel features but often overfit the channel ordering, which hampers adaptation when channels are added or reordered. Channel-indep…
We introduce Hybrid Space-aware Stochastic Convolution Attention Noise (HySCAN), a hybrid randomized defense that helps close the long-standing gap between provable robustness under ℓ2 certificates and empirical robustness against strong ℓ∞ attacks, while maintaining strong generalization across div…
With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inconsistencies. In singing, rhythmic vocalization weakens this coupling and introduces a nontrivial dom…
We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main aspects: speech understanding, audio scene understanding, and vo…
Recent speech-LLMs have shown impressive performance in tasks like transcription and translation, yet they remain limited in understanding the paralinguistic aspects of speech crucial for social and emotional intelligence. We propose CP-Bench, a benchmark for evaluating speech-LLMs on contextual par
The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder…
When planning for autonomous driving, it is crucial to consider essential traffic elements such as lanes, intersections, traffic regulations, and dynamic agents. However, they are often overlooked by the traditional end-to-end planning methods, likely leading to inefficiencies and non-compliance wit
Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception…
Following the success of Large Language Models (LLMs) in language tasks, LLMs have been adapted for reasoning in math word problems (MWPs). MWP is a complex task that requires both semantic understanding of text and mathematical reasoning, such that achieving high accuracy in MWP remains a challenge…
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising…
Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work we introduce Universal Semi-Supervised Domain Adaptation (UniSSDA) a practical yet challenging setting where the targe…
This letter presents a safety trajectory planning and tracking architecture for a quadrotor autopilot. Motor saturation constraints are explicitly considered in obstacle avoidance mission. Two challenging cases are covered: agile flight with a short task time and stable flight with actuator degradat
In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ab…
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain. Large-data pre-trained networks are used to initialize source models during source training, and subsequently discarded. However, source training can cause the mo…
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data. Altho…
Online prediction for streaming time series data has practical use for many real-world applications where downstream decisions depend on accurate forecasts for the future. Deployment in dynamic environments requires models to adapt quickly to changing data distributions without overfitting. We propo…
While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications. Domain generalization addresses this issue by employing multip…
Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with un-known workpieces so that building predictive models which can generalize over a number of these objects is highly desirable. In th…
Heterogeneous sensor data fusion is a challenging field that has gathered significant interest in recent years. In this paper, we propose a neural network-based multimodal data fusion framework named deep multimodal encoder (DME). Through our new objective function, both the intra- and inter-modal c…