Search Results for author:
Found 43 papers, 24 papers with code
DeltaDPD: Exploiting Dynamic Temporal Sparsity in Recurrent Neural Networks for Energy-Efficient Wideband Digital Predistortion
Digital Predistortion (DPD) is a popular technique to enhance signal quality in wideband RF power amplifiers (PAs).
RadMamba: Efficient Human Activity Recognition through Radar-based Micro-Doppler-Oriented Mamba State-Space Model
To leverage the strengths of transformer architectures while simultaneously enhancing accuracy and reducing computational complexity, this paper introduces RadMamba, a parameter-efficient, radar micro-Doppler-oriented Mamba SSM specifically tailored for radar-based HAR.
Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs
In this paper, we conducted an extensive investigation into various LLMs and revealed three significant discoveries: (1) the layerwise pruning sensitivity (LPS) of LLMs is highly non-uniform, (2) the choice of pruning metric affects LPS, and (3) the performance of a sparse model is related to the uniformity of its layerwise redundancy level.
SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
To mitigate the lack of publicly available datasets, we compile an extensive dataset that includes 110K GitHub issues along with their corresponding patches and train the two models of SWE-Fixer separately.
Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs
In this study, we thoroughly investigate the application of V:N:M sparsity in vision models and LLMs across multiple tasks, from pertaining to downstream tasks.
Deep Uncertainty-aware Tracking for Maneuvering Targets
When tracking maneuvering targets, model-driven approaches encounter difficulties in comprehensively delineating complex real-world scenarios and are prone to model mismatch when the targets maneuver.
Multi-frame Detection via Graph Neural Networks: A Link Prediction Approach
As to applying graph neural networks in multi-frame detection, the algorithms are primarily based on node classification tasks, which cannot directly output target tracks.
DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm$^2$ Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion
The increasing adoption of Deep Neural Network (DNN)-based Digital Pre-distortion (DPD) in modern communication systems necessitates efficient hardware implementations.
CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning
This paper presents CleanUMamba, a time-domain neural network architecture designed for real-time causal audio denoising directly applied to raw waveforms.
SlimSeiz: Efficient Channel-Adaptive Seizure Prediction Using a Mamba-Enhanced Network
SlimSeiz operates in two states: the first stage selects the optimal channel set for seizure prediction using machine learning algorithms, and the second stage employs a lightweight neural network based on convolution and Mamba for prediction.
FACET: Fast and Accurate Event-Based Eye Tracking Using Ellipse Modeling for Extended Reality
Eye tracking is a key technology for gaze-based interactions in Extended Reality (XR), but traditional frame-based systems struggle to meet XR's demands for high accuracy, low latency, and power efficiency.
1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit
The strategy leverages the heterogeneity of gradients by pruning less informative gradients and enhancing the numerical precision of remaining gradients to mitigate gradient variance.
Hardware Neural Control of CartPole and F1TENTH Race Car
We demonstrate kHz control rates for a physical cartpole and offloading control to the FPGA hardware on the F1TENTH car.
DeltaKWS: A 65nm 36nJ/Decision Bio-inspired Temporal-Sparsity-Aware Digital Keyword Spotting IC with 0.6V Near-Threshold SRAM
This paper introduces DeltaKWS, to the best of our knowledge, the first $\Delta$RNN-enabled fine-grained temporal sparsity-aware KWS IC for voice-controlled devices.
MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers
Applied to a 160MHz-BW 1024-QAM OFDM signal from a digital RF PA, MP-DPD gives no performance loss against 32-bit floating-point precision DPDs, while achieving -43. 75 (L)/-45. 27 (R) dBc in Adjacent Channel Power Ratio (ACPR) and -38. 72 dB in Error Vector Magnitude (EVM).
Event-Based Eye Tracking. AIS 2024 Challenge Survey
This survey reviews the AIS 2024 Event-Based Eye Tracking (EET) Challenge.
FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models
The rapid development of large language model (LLM) evaluation methodologies and datasets has led to a profound challenge: integrating state-of-the-art evaluation techniques cost-effectively while ensuring reliability, reproducibility, and efficiency.
CodeShell Technical Report
Through this process, We have curated 100 billion high-quality pre-training data from GitHub.
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse.
KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models
Automatic evaluation methods for large language models (LLMs) are hindered by data contamination, leading to inflated assessments of their effectiveness.
Epilepsy Seizure Detection and Prediction using an Approximate Spiking Convolutional Transformer
Epilepsy is a common disease of the nervous system.
OpenDPD: An Open-Source End-to-End Learning & Benchmarking Framework for Wideband Power Amplifier Modeling and Digital Pre-Distortion
With the rise in communication capacity, deep neural networks (DNN) for digital pre-distortion (DPD) to correct non-linearity in wideband power amplifiers (PAs) have become prominent.
Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training
Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware.
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other instances and lack task-level consistency across the selected few-shot examples.
Online Relocating and Matching of Ride-Hailing Services: A Model-Based Modular Approach
This study proposes an innovative model-based modular approach (MMA) to dynamically optimize order matching and vehicle relocation in a ride-hailing platform.
JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
Instruction tuning is vital for enhancing the performance of large language models (LLMs), but existing text-to-text methods, referred to as TextTuning, struggle with issues such as generalization, robustness, and controllability due to their lack of explicit task structures.
3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network
This paper presents a sparse Change-Based Convolutional Long Short-Term Memory (CB-ConvLSTM) model for event-based eye tracking, key for next-generation wearable healthcare technology such as AR/VR headsets.
To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Acceleration
The power efficiency of the biological brain outperforms any large-scale deep learning ( DL ) model; thus, neuromorphic computing tries to mimic the brain operations, such as spike-based information processing, to improve the efficiency of DL models.
M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models
M3Exam exhibits three unique characteristics: (1) multilingualism, encompassing questions from multiple countries that require strong multilingual proficiency and cultural knowledge; (2) multimodality, accounting for the multimodal nature of many exam questions to test the model's multimodal understanding capability; and (3) multilevel structure, featuring exams from three critical educational periods to comprehensively assess a model's proficiency at different levels.
Easy-to-Hard Learning for Information Extraction
Information extraction (IE) systems aim to automatically extract structured information, such as named entities, relations between entities, and events, from unstructured texts.
Towards Generalizable and Robust Text-to-SQL Parsing
Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries.
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems.
A Projection-Based K-space Transformer Network for Undersampled Radial MRI Reconstruction with Limited Training Subjects
However, non-Cartesian trajectories such as the radial trajectory need to be transformed onto a Cartesian grid in each iteration of the network training, slowing down the training process and posing inconvenience and delay during training.
UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue
The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document.
Skydiver: A Spiking Neural Network Accelerator Exploiting Spatio-Temporal Workload Balance
Spiking Neural Networks (SNNs) are developed as a promising alternative to Artificial Neural networks (ANNs) due to their more realistic brain-inspired computing models.
Spiking Cochlea with System-level Local Automatic Gain Control
The bandpass filter gain of a channel is adapted dynamically to the input amplitude so that the average output spike rate stays within a defined range.
Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity
The pruned networks running on Spartus hardware achieve weight sparsity levels of up to 96% and 94% with negligible accuracy loss on the TIMIT and the Librispeech datasets.
Ranking Items in Large-Scale Item Search Engines with Reinforcement Learning
Ranking items in large-scale item search engines such as Amazon and Taobao is a typical multi-step decision-making problem.
Recurrent Neural Network Control of a Hybrid Dynamic Transfemoral Prosthesis with EdgeDRNN Accelerator
Lower leg prostheses could improve the life quality of amputees by increasing comfort and reducing energy to locomote, but currently control methods are limited in modulating behaviors based upon the human's experience.
EdgeDRNN: Enabling Low-latency Recurrent Neural Network Edge Inference
This paper presents a Gated Recurrent Unit (GRU) based recurrent neural network (RNN) accelerator called EdgeDRNN designed for portable edge computing.
ReCoNet: Real-time Coherent Video Style Transfer Network
Image style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos.
Ranked #8 on
Semantic Segmentation
on FMB Dataset
DeepSketch2Face: A Deep Learning Based Sketching System for 3D Face and Caricature Modeling
This system has a labor-efficient sketching interface, that allows the user to draw freehand imprecise yet expressive 2D lines representing the contours of facial features.
