Related papers: Real-Time Inference for Distributed Multimodal Sys…
Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head…
Action-feedback delay during operation reduces both task performance and sense of agency (SoA). In this study, using information-theoretic free energy, we formalized a novel mathematical model for explaining the influence of delay on both…
Language model (LM)-based embodied agents are increasingly deployed in real-world settings. Yet, their adaptability remains limited in dynamic environments, where constructing accurate and flexible world models is crucial for effective…
Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in appearance, motion pattern, and catagory between the…
As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization…
This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to…
Test-Time Adaptation (TTA) aims to tackle distribution shifts using unlabeled test data without access to the source data. In the context of multimodal data, there are more complex noise patterns than unimodal data such as simultaneous…
Event cameras offer unique advantages for vision tasks in challenging environments, yet processing asynchronous event streams remains an open challenge. While existing methods rely on specialized architectures or resource-intensive…
In this paper, a novel time-based modulation scheme is proposed in the time-asynchronous channel for diffusion-based molecular communication systems with drift. Based on this modulation scheme, we demonstrate that the sample variance of…
Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex SDS models address this by predicting output continuously,…
Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency, limiting them to low-frequency batch-and-execute paradigm. This frequency mismatch creates an execution blind spot,…
Developing semi-supervised task-oriented dialog (TOD) systems by leveraging unlabeled dialog data has attracted increasing interests. For semi-supervised learning of latent state TOD models, variational learning is often used, but suffers…
Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with…
A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual…
Compound AI (cAI) systems chain multiple AI models to solve complex problems. cAI systems are typically composed of deep neural networks (DNNs), transformers, and large language models (LLMs), exhibiting a high degree of computational…
Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where…
Wireless systems beyond 5G evolve towards embracing both sensing and communication, resulting in increased convergence of the digital and the physical world. The existence of fused digital-physical realms raises critical questions regarding…
Robust robotic manipulation requires not only predicting how the scene evolves over time, but also recognizing task-relevant objects in complex scenes. However, existing VLA models face two limitations. They typically act only on the…
Urban forecasting models often face a severe data imbalance problem: only a few cities have dense, long-span records, while many others expose short or incomplete histories. Direct transfer from data-rich to data-scarce cities is unreliable…
As data from IoT (Internet of Things) sensors become ubiquitous, state-of-the-art machine learning algorithms face many challenges on directly using sensor data. To overcome these challenges, methods must be designed to learn directly from…