Search Results for author:
Found 11 papers, 4 papers with code
MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula
In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into $LaTeX$ Formulas for Improved Readability
Even if we try to solve this using language models, there is no paired data between spoken sentences and LaTeX formulas to train it.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models
Mixture-of-Experts (MoE) large language models (LLM) have memory requirements that often exceed the GPU memory capacity, requiring costly parameter movement from secondary memories to the GPU for expert computation.
ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation System
The model size growth of personalized recommendation systems poses new challenges for inference.
EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation
However, to apply local attention successfully for EIs, a specific strategy, which addresses distorted equirectangular geometry and limited receptive field simultaneously, is required.
Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning
Due to difficulties in acquiring ground truth depth of equirectangular (360) images, the quality and quantity of equirectangular depth data today is insufficient to represent the various scenes in the world.
Ranked #3 on
Depth Estimation
on Stanford2D3D Panoramic
Active Learning for Deep Object Detection via Probabilistic Modeling
Most of these methods are based on multiple models or are straightforward extensions of classification methods, hence estimate an image's informativeness using only the classification head.
GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent
In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training.
Deep Active Learning for Object Detection with Mixture Density Networks
For active learning, we propose a scoring function that aggregates uncertainties from both the classification and the localization outputs of the network.
Layer-specific Optimization for Mixed Data Flow with Mixed Precision in FPGA Design for CNN-based Object Detectors
The proposed design employs two layer-specific optimizations: layer-specific mixed data flow and layer-specific mixed precision.
Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving
Therefore, a detection algorithm that can cope with mislocalizations is required in autonomous driving applications.
