14 accepted papers
This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method ensures chunk coherence and minimizes semantic fragmentation.
Self-attention dominates the computational and memory cost of long-context LLM inference across both prefill and decode phases. To address this challenge, we introduce **Sketch\&Walk** Attention, a training-free sparse attention method that determines sparsity with lightweight sketches and determini…
The scaling of Generative AI (GenAI) models into the hundreds of billions of parameters makes low-precision computation indispensable for efficient deployment. We argue that the fundamental solution lies in developing low-precision \emph{floating-point} formats, which inherently provide numerical st…
Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing highly consistent multi-view images. However, due to t…
Autonomous driving datasets are essential for validating the progress of intelligent vehicle algorithms, which include localization, perception, and prediction. However, existing datasets are predominantly focused on structured urban environments, which limits the exploration of unstructured and spe
Deep learning has achieved significant success but poses increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of understanding of their energy efficiency during inference. In this study, we conduct a comprehensive analysis of the inference energy c…
Detecting user frustration in modern-day task-oriented dialog (TOD) systems is imperative for maintaining overall user satisfaction, engagement, and retention. However, most recent research is focused on sentiment and emotion detection in academic settings, thus failing to fully encapsulate implicat…
Nowadays, singing voice conversion (SVC) has made great strides in both naturalness and similarity for common SVC with a neutral expression. However, besides singer identity, emotional expression is also essential to convey the singer’s emotions and attitudes, but current SVC systems can not effecti…
Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene Structure: Existing methods struggle to reveal the spatial an…
3D representation is essential to the significant advance of 3D generation with 2D diffusion priors. As a flexible representation, NeRF has been first adopted for 3D representation. With density-based volumetric rendering, it however suffers both intensive computational overhead and inaccurate mesh…
"Generating multi-camera street-view videos is critical for augmenting autonomous driving datasets, addressing the urgent demand for extensive and varied data. Due to the limitations in diversity and challenges in handling lighting conditions, traditional rendering-based methods are increasingly bei…
Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introdu…
Achieving instinctive multi-grasp control of prosthetic hands typically still requires a large number of sensors, such as electromyography (EMG) electrodes mounted on a residual limb, that can be costly and time consuming to position, with their signals difficult to classify. Deep-learning-based EMG…
Virtual reality (VR) rehabilitation systems have been proposed to enable prosthetic hand users to perform training before receiving their prosthesis. Improving pre-prosthetic training to be more representative and better prepare the patient for prosthesis use is a crucial step forwards in rehabilita