Related papers: Since U Been Gone: Augmenting Context-Aware Transc…
Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target generation. This restricted, single-view perspective lacks sufficient temporal and…
As social VR applications grow in popularity, blind and low vision users encounter continued accessibility barriers. Yet social VR, which enables multiple people to engage in the same virtual space, presents a unique opportunity to allow…
This paper introduces an augmented reality (AR) captioning framework designed to support Deaf and Hard of Hearing (DHH) learners in STEM classrooms by integrating non-verbal emotional cues into live transcriptions. Unlike conventional…
In this paper, we show that unwinding the rotations of a user immersed in a telepresence robot is preferred and may increase the feeling of presence or "being there". By immersive telepresence, we mean a scenario where a user wearing a…
Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational…
Traditional customer support systems, such as Interactive Voice Response (IVR), rely on rigid scripts and lack the flexibility required for handling complex, policy-driven tasks. While large language model (LLM) agents offer a promising…
Augmented reality (AR) games, particularly those designed for head-mounted displays, have grown increasingly prevalent. However, most existing systems depend on pre-scanned, static environments and rely heavily on continuous tracking or…
Learning feature interaction is the critical backbone to building recommender systems. In web-scale applications, learning feature interaction is extremely challenging due to the sparse and large input feature space; meanwhile, manually…
In virtual reality environments, the alignment of perceptual modalities is crucial for immersion and presence. In the AR domain, it is difficult to create such alignments because elements in the physical world are often beyond the user's…
The capacity to create realistic virtual humans has progressed significantly, and such characters can be found in many applications across entertainment, education and health. As an essential element of interactive virtual humans,…
We propose augmenting immersive telepresence by adding a virtual body, representing the user's own arm motions, as realized through a head-mounted display and a 360-degree camera. Previous research has shown the effectiveness of having a…
This study is the first to explore the interplay between haptic interaction and avatar representation in Shared Virtual Environments (SVEs). Specifically, how these factors shape users' sense of social presence during dyadic collaborations,…
Group conversations are valuable for second language (L2) learners as they provide opportunities to practice listening and speaking, exercise complex turn-taking skills, and experience group social dynamics in a target language. However,…
Recording the dynamics of unscripted human interactions in the wild is challenging due to the delicate trade-offs between several factors: participant privacy, ecological validity, data fidelity, and logistical overheads. To address these,…
Fueled by advances in multi-party communications, increasingly mature immersive technologies being adopted, and the COVID-19 pandemic, a new wave of social virtual reality (VR) platforms have emerged to support socialization, interaction,…
Why do some speakers capture a room almost instantly while others fail to connect? The real-time architecture of audience engagement remains largely a black box. Here, we used motion-captured animations to present the pure nonverbal…
Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…
We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection between the quality of generation and the representations…
Recommendation systems have traditionally relied on short-term engagement signals, such as clicks and likes, to personalize content. However, these signals are often noisy, sparse, and insufficient for capturing long-term user satisfaction…
Our world is not static and humans naturally cause changes in their environments through interactions, e.g., opening doors or moving furniture. Modeling changes caused by humans is essential for building digital twins, e.g., in the context…