Search Results for author:
Found 10 papers, 3 papers with code
Continuous Speech Tokenizer in Text To Speech
Our results show that the speech language model based on the continuous speech tokenizer has better continuity and higher estimated Mean Opinion Scores (MoS).
Direct Preference Knowledge Distillation for Large Language Models
Meanwhile, we prove the value and effectiveness of the introduced implicit reward and output preference in KD through experiments and theoretical analysis.
From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding
By aligning the classes of previous datasets to our semantic space, we gather (image/video/skeleton/MoCap) datasets into a unified database in a unified label system, i. e., bridging "isolated islands" into a "Pangea".
DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design
In this paper, for the first time, we propose DeepOHeat, a physics-aware operator learning framework to predict the temperature field of a family of heat equations with multiple parametric or non-parametric design configurations.
Systolic-CNN: An OpenCL-defined Scalable Run-time-flexible FPGA Accelerator Architecture for Accelerating Convolutional Neural Network Inference in Cloud/Edge Computing
Systolic-CNN is also run-time-flexible in the context of multi-tenancy cloud/edge computing, which can be time-shared to accelerate a variety of CNN models at run time without the need of recompiling the FPGA kernel hardware nor reprogramming the FPGA.
Light-Weight RetinaNet for Object Detection
On the contrary, very few studies discuss the computation and accuracy trade-off scheme for mAP-30-tier detection networks.
Build a Compact Binary Neural Network through Bit-level Sensitivity and Data Pruning
Emerging solutions are adopted for the neural network compression, e. g., bina-ry/ternary weight network, pruned network and quantized network.
A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks
For processing static data in large batch sizes, the proposed solution is on a par with a Titan X GPU in terms of throughput while delivering 9. 5x higher energy efficiency.
A Data-Driven Compressive Sensing Framework Tailored For Energy-Efficient Wearable Sensing
Compressive sensing (CS) is a promising technology for realizing energy-efficient wireless sensors for long-term health monitoring.
A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing
In this paper, we develop a binary convolutional encoder-decoder network (B-CEDNet) for natural scene text processing (NSTP).
