Search Results for author:
Found 17 papers, 3 papers with code
EDENet: Echo Direction Encoding Network for Place Recognition Based on Ground Penetrating Radar
Ground penetrating radar (GPR) based localization has gained significant recognition in robotics due to its ability to detect stable subsurface features, offering advantages in environments where traditional sensors like cameras and LiDAR may struggle.
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
We present PASTA, a learning-based system that teaches LLMs to identify semantic independence and express parallel decoding opportunities in their own responses.
FedMobileAgent: Training Mobile Agents Using Decentralized Self-Sourced Data from Diverse Users
To tackle these challenges, we propose FedMobileAgent, a collaborative framework that trains mobile agents using self-sourced data from diverse users.
The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
Pruning eliminates unnecessary parameters in neural networks; it offers a promising solution to the growing computational demands of large language models (LLMs).
The Moral Case for Using Language Model Agents for Recommendation
Our information and communication environment has fallen short of the ideals that networked global communication might have served.
Using Geometrical information to Measure the Vibration of A Swaying Millimeter-wave Radar
This paper presents two new, simple yet effective approaches to measure the vibration of a swaying millimeter-wave radar (mmRadar) utilizing geometrical information.
BERT: Accelerating Vital Signs Measurement for Bioradar with An Efficient Recursive Technique
Recent years have witnessed the great advance of bioradar system in smart sensing of vital signs (VS) for human healthcare monitoring.
Self-Selected Attention Span for Accelerating Large Language Model Inference
We demonstrate that using this custom CUDA kernel improves the throughput of LLM inference by 28%.
Striped Attention: Faster Ring Attention for Causal Transformers
In experiments running Striped Attention on A100 GPUs and TPUv4s, we are able to achieve up to 1. 45x end-to-end throughput improvements over the original Ring Attention algorithm on causal transformer training at a sequence length of 256k.
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense scaling -- and their effects on two core capabilities of LLMs: (a) recalling facts presented during pre-training and (b) processing information presented in-context during inference.
The Effect of Data Dimensionality on Neural Network Prunability
Practitioners prune neural networks for efficiency gains and generalization improvements, but few scrutinize the factors determining the prunability of a neural network the maximum fraction of weights that pruning can remove without compromising the model's test accuracy.
Pruning's Effect on Generalization Through the Lens of Training and Regularization
Pruning models in this over-parameterized regime leads to a contradiction -- while theory predicts that reducing model size harms generalization, pruning to a range of sparsities nonetheless improves it.
Compiling ONNX Neural Network Models Using MLIR
Deep neural network models are becoming increasingly popular and have been used in various tasks such as computer vision, speech recognition, and natural language processing.
Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions
In this paper, we propose \textbf{N3} (\textbf{N}eural \textbf{N}etworks from \textbf{N}atural Language) - a new paradigm of synthesizing task-specific neural networks from language descriptions and a generic pre-trained model.
Novel Co-variant Feature Point Matching Based on Gaussian Mixture Model
In this paper, we develop a novel method considering all the feature center position coordinates, the local feature shape and orientation information based on Gaussian Mixture Model for co-variant feature matching.
Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar
In this work, we propose a neural network architecture, namely segmented convolutional gated recurrent neural network (SCGRNN), to recognize human activities based on micro-Doppler spectrograms measured by the ultra-wideband radar.
Clustering Bioactive Molecules in 3D Chemical Space with Unsupervised Deep Learning
We ex-plored the superior learning capability of deep autoencoders for unsupervised clustering of 1. 39 mil-lion bioactive molecules into band-clusters in a 3-dimensional latent chemical space.
