Search Results for author:
Found 82 papers, 36 papers with code
FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
Current video generative foundation models primarily focus on text-to-video tasks, providing limited control for fine-grained video content creation.
Speculative Decoding for Verilog: Speed and Quality, All in One
The rapid advancement of large language models (LLMs) has revolutionized code generation tasks across various programming languages.
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Video inpainting, which aims to restore corrupted video content, has experienced substantial progress.
DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis
This paper introduces DeepCircuitX, a comprehensive repository-level dataset designed to advance RTL (Register Transfer Level) code understanding, generation, and power-performance-area (PPA) analysis.
DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
Recent advancements in large language models (LLMs) have shown significant potential for automating hardware description language (HDL) code generation from high-level natural language instructions.
Dyve: Thinking Fast and Slow for Dynamic Process Verification
We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory.
DeepCell: Multiview Representation Learning for Post-Mapping Netlists
Representation learning for post-mapping (PM) netlists is a critical challenge in Electronic Design Automation (EDA), driven by the diverse and complex nature of modern circuit designs.
DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
Circuit representation learning has become pivotal in electronic design automation, enabling critical tasks such as testability analysis, logic reasoning, power estimation, and SAT solving.
DebugAgent: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging
Despite the significant success of deep learning models in computer vision, they often exhibit systematic failures on specific data subsets, known as error slices.
BrushEdit: All-In-One Image Inpainting and Editing
Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods.
LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation
Recently, text-to-image models based on diffusion have achieved remarkable success in generating high-quality images.
MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
The rapid advancement of diffusion models has greatly improved video synthesis, especially in controllable video generation, which is essential for applications like autonomous driving.
DeepSeq2: Enhanced Sequential Circuit Learning with Disentangled Representations
Circuit representation learning is increasingly pivotal in Electronic Design Automation (EDA), serving various downstream tasks with enhanced model efficiency and accuracy.
Vector Quantization Prompting for Continual Learning
In this way, VQ-Prompt can optimize the prompt selection process with task loss and meanwhile achieve effective abstraction of task knowledge for continual learning.
MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls
However, employing a unified model to achieve various generation tasks with different condition modalities presents two main challenges: motion distribution drifts across different tasks (e. g., co-speech gestures and text-driven daily actions) and the complex optimization of mixed conditions with varying granularities (e. g., text and audio).
OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection
While open-source LLMs offer solutions to these concerns, they typically underperform commercial models in RTL code generation tasks, primarily due to the scarcity of high-quality open-source RTL datasets.
Image Inpainting Models are Effective Tools for Instruction-guided Image Editing
The most advanced methods, such as SmartEdit and MGIE, usually combine large language models with diffusion models through joint training, where the former provides text understanding ability, and the latter provides image generation ability.
DeepGate3: Towards Scalable Circuit Representation Learning
Circuit representation learning has shown promising results in advancing the field of Electronic Design Automation (EDA).
MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
Sora's high-motion intensity and long consistent videos have significantly impacted the field of video generation, attracting unprecedented attention.
DSPO: An End-to-End Framework for Direct Sorted Portfolio Construction
In quantitative investment, constructing characteristic-sorted portfolios is a crucial strategy for asset allocation.
MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes
While controllable generative models for images and videos have achieved remarkable success, high-quality models for 3D scenes, particularly in unbounded scenarios like autonomous driving, remain underdeveloped due to high data acquisition costs.
Beyond Trend and Periodicity: Guiding Time Series Forecasting with Textual Cues
This work introduces a novel Text-Guided Time Series Forecasting (TGTSF) task.
DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
Furthermore, image syntheses from DetDiffusion can effectively augment training data, significantly enhancing downstream detection performance.
BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
Image inpainting, the process of restoring corrupted images, has seen significant advancements with the advent of diffusion models (DMs).
Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis.
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Recent advancements in Text-to-Image (T2I) models have raised significant safety concerns about their potential misuse for generating inappropriate or Not-Safe-For-Work (NSFW) contents, despite existing countermeasures such as NSFW classifiers or model fine-tuning for inappropriate concept removal.
Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
In this study, we present aLLM4TS, an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning.
Text Image Inpainting via Global Structure-Guided Diffusion Models
Leveraging the global structure of the text as a prior, the proposed GSDM develops an efficient diffusion model to recover clean texts.
LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
Since circuit can be represented with HDL in a textual format, it is reasonable to question whether LLMs can be leveraged in the EDA field to achieve fully automated chip design and generate circuits with improved power, performance, and area (PPA).
Non-Cross Diffusion for Semantic Consistency
In diffusion models, deviations from a straight generative flow are a common issue, resulting in semantic inconsistencies and suboptimal generations.
MMA-Diffusion: MultiModal Attack on Diffusion Models
In recent years, Text-to-Image (T2I) models have seen remarkable advancements, gaining widespread adoption.
MagicDrive: Street View Generation with Diverse 3D Geometry Control
Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control.
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Specifically, in the context of diffusion-based editing, where a source image is edited according to a target prompt, the process commences by acquiring a noisy latent vector corresponding to the source image via the diffusion model.
Ranked #5 on
Text-based Image Editing
on PIE-Bench
DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models
There is a recent work that directly applies it to OOD detection, which employs a conditional Generative Adversarial Network (cGAN) to enlarge semantic mismatch in the image space.
Generative Adversarial Network
Out-of-Distribution Detection
FITS: Modeling Time Series with $10k$ Parameters
In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis.
Ranked #25 on
Time Series Forecasting
on ETTh1 (336) Multivariate
DeepGate2: Functionality-Aware Circuit Representation Learning
Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks.
HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation
While such a plug-and-play approach is appealing, the inevitable and uncertain conflicts between the original images produced from the frozen SD branch and the given condition incur significant challenges for the learnable branch, which essentially conducts image feature editing for condition enforcement.
Pi-ViMo: Physiology-inspired Robust Vital Sign Monitoring using mmWave Radars
In this paper, we address these limitations and present "Pi-ViMo", a non-contact Physiology-inspired Robust Vital Sign Monitoring system, using mmWave radars.
Active Teacher for Semi-Supervised Object Detection
In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{https://github. com/HunterJ-Lin/ActiveTeacher}) for semi-supervised object detection (SSOD).
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes
Humans have long been recorded in a variety of forms since antiquity.
DeepSeq: Deep Sequential Circuit Learning
Circuit representation learning is a promising research direction in the electronic design automation (EDA) field.
FrAug: Frequency Domain Augmentation for Time Series Forecasting
In time series forecasting (TSF), we need to model the fine-grained temporal relationship within time series segments to generate accurate forecasting results given data in a look-back window.
On Function-Coupled Watermarks for Deep Neural Networks
Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN providers implant secret information into the model so that they can later claim IP ownership by retrieving their embedded watermarks with some dedicated trigger inputs.
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification
Third, performing data selection in the SSAL setting can achieve a significant and consistent performance improvement, especially with abundant unlabeled data.
Monolingual Recognizers Fusion for Code-switching Speech Recognition
It has two stages: the speech awareness (SA) stage and the language fusion (LF) stage.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection
Based on the finding that multiple different modules in image acquisition will lead to different sensitivity inconsistencies to the convolutional neural network (CNN)-based rendering in images, we propose a deep texture rendering module for texture difference enhancement and discriminative texture representation.
SATformer: Transformer-Based UNSAT Core Learning
This paper introduces SATformer, a novel Transformer-based approach for the Boolean Satisfiability (SAT) problem.
Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning
Empowered by the robust relation net built on SSL, we found that BEYOND outperforms baselines in terms of both detection ability and speed.
Out-of-Distribution Detection with Semantic Mismatch under Masking
This paper proposes a novel out-of-distribution (OOD) detection framework named MoodCat for image classifiers.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Language-specific Characteristic Assistance for Code-switching Speech Recognition
Dual-encoder structure successfully utilizes two language-specific encoders (LSEs) for code-switching speech recognition.
DeepTPI: Test Point Insertion with Deep Reinforcement Learning
Unlike previous learning-based solutions that formulate the TPI task as a supervised-learning problem, we train a novel DRL agent, instantiated as the combination of a graph neural network (GNN) and a Deep Q-Learning network (DQN), to maximize the test coverage improvement.
DeepSAT: An EDA-Driven Learning Framework for SAT
Based on this observation, we approximate the SAT solving procedure with a conditional generative model, leveraging a novel directed acyclic graph neural network (DAGNN) with two polarity prototypes for conditional SAT modeling.
Are Transformers Effective for Time Series Forecasting?
Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task.
Ranked #1 on
Time Series Forecasting
on ETTh1 (96) Univariate
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation
This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch.
Ranked #1 on
2D Human Pose Estimation
on JHMDB (2D poses only)
What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
For legitimate inputs that are correctly inferred, the synthetic output tries to reconstruct the input.
SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as a side-effect.
DeepFIB: Self-Imputation for Time Series Anomaly Detection
Due to the inherently unpredictable and highly varied nature of anomalies and the lack of anomaly labels in historical data, the AD problem is typically formulated as an unsupervised learning problem.
Testability-Aware Low Power Controller Design with Evolutionary Learning
The proposed GA-guided XORNets also allows reducing the number of control bits, and the total testing time decreases by 20. 78% on average and up to 47. 09% compared to the existing design without sacrificing test coverage.
DeepGate: Learning Neural Representations of Logic Gates
We propose DeepGate, a novel representation learning solution that effectively embeds both logic function and structural information of a circuit as vectors on each gate.
T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis
In this work, we propose a novel tree-structured wavelet neural network for time series signal analysis, namely T-WaveNet, by taking advantage of an inherent property of various types of signals, known as the dominant frequency range.
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory.
Ranked #32 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Information Bottleneck Approach to Spatial Attention Learning
Extensive experiments show that the proposed IB-inspired spatial attention mechanism can yield attention maps that neatly highlight the regions of interest while suppressing backgrounds, and bootstrap standard DNN structures for visual recognition tasks (e. g., image classification, fine-grained recognition, cross-domain classification).
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences.
Ranked #1 on
Time Series Forecasting
on ETTh1 (24) Multivariate
(using extra training data)
Relational Graph Neural Network Design via Progressive Neural Architecture Search
We propose a novel solution to addressing a long-standing dilemma in the representation learning of graph neural networks (GNNs): how to effectively capture and represent useful information embedded in long-distance nodes to improve the performance of nodes with low homophily without leading to performance degradation in nodes with high homophily.
TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
To be specific, we first build a similarity graph on test instances and training samples, and we conduct graph-based semi-supervised learning to extract contextual features.
AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions.
Skimming and Scanning for Untrimmed Video Action Recognition
Video action recognition (VAR) is a primary task of video understanding, and untrimmed videos are more common in real-life scenes.
MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
Consequently, we propose a novel learning-based solution to model such contradictions for AE detection.
T-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series Analysis
Motivated by the fact that usually a small subset of the frequency components carries the primary information for sensor data, we propose a novel tree-structured wavelet neural network for sensor data analysis, namely \emph{T-WaveNet}.
DeepDyve: Dynamic Verification for Deep Neural Networks
The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much.
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach
With the reduced dimensionality of less relevant body areas, the training set distribution within network branches more closely reflects the statistics of local poses instead of global body poses, without sacrificing information important for joint inference.
Ranked #21 on
Monocular 3D Human Pose Estimation
on Human3.6M
The Effect of the Multi-Layer Text Summarization Model on the Efficiency and Relevancy of the Vector Space-based Information Retrieval
The purpose of this research is to measure the effect of the Multi-Layer Similarity model of the automatic text summarization on building an informative and condensed invert index in the IR systems.
ICSTrace: A Malicious IP Traceback Model for Attacking Data of Industrial Control System
Considering the attacks against industrial control system are mostly organized and premeditated actions, IP traceback is significant for the security of industrial control system.
DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image
In this paper, we propose a two-stage fully 3D network, namely \textbf{DeepFuse}, to estimate human pose in 3D space by fusing body-worn Inertial Measurement Unit (IMU) data and multi-view images deeply.
Ranked #5 on
3D Human Pose Estimation
on Total Capture
Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples
Deep neural networks (DNNs) are shown to be susceptible to adversarial example attacks.
On Functional Test Generation for Deep Neural Network IPs
Considering the large amount of training data and know-how required to generate the network, it is more practical to use third-party DNN intellectual property (IP) cores for many designs.
nuScenes: A multimodal dataset for autonomous driving
Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar.
Ranked #316 on
3D Object Detection
on nuScenes
(using extra training data)
Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image
Experimental results show that the proposed structure-aware 3D hourglass network is able to achieve a mean joint error of 7. 4 mm in MSRA and 8. 9 mm in NYU datasets, respectively.
On Configurable Defense against Adversarial Example Attacks
Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications.
Invocation-driven Neural Approximate Computing with a Multiclass-Classifier and Multiple Approximators
We thus propose a novel approximate computing architecture with a Multiclass-Classifier and Multiple Approximators (MCMA).
I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators
Deep learning has become the de-facto computational paradigm for various kinds of perception problems, including many privacy-sensitive applications such as online medical image analysis.
Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks
Previous adversarial example crafting methods, however, use simple metrics to evaluate the distances between the original examples and the adversarial ones, which could be easily detected by human eyes.
