Search Results for author:
Found 75 papers, 30 papers with code
Hummus: A Dataset of Humorous Multimodal Metaphor Use
Metaphor and humor share a lot of common ground, and metaphor is one of the most common humorous mechanisms.
THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models
On-device deep learning (DL) has rapidly gained adoption in mobile apps, offering the benefits of offline model inference and user privacy preservation over cloud-based approaches.
Visual Acuity Consistent Foveated Rendering towards Retinal Resolution
Prior foveated rendering methods often suffer from a limitation where the shading load escalates with increasing display resolution, leading to decreased efficiency, particularly when dealing with retinal-level resolutions.
Cross-Domain Underwater Image Enhancement Guided by No-Reference Image Quality Assessment: A Transfer Learning Approach
Single underwater image enhancement (UIE) is a challenging ill-posed problem, but its development is hindered by two major issues: (1) The labels in underwater reference datasets are pseudo labels, relying on these pseudo ground truths in supervised learning leads to domain discrepancy.
Life-Cycle Routing Vulnerabilities of LLM Router
While previous studies have primarily focused on routing efficiency, security vulnerabilities throughout the entire LLM router life cycle, from training to inference, remain largely unexplored.
Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions
The adaptivity and maneuvering capabilities of Autonomous Underwater Vehicles (AUVs) have drawn significant attention in oceanic research, due to the unpredictable disturbances and strong coupling among the AUV's degrees of freedom.
Data-Efficient Model for Psychological Resilience Prediction based on Neurological Data
In the test stage, a new noise-informed inference algorithm is proposed to address the low signal-to-noise ratio of the neurological data.
Confidence Interval Construction and Conditional Variance Estimation with Dense ReLU Networks
Building on this, for a ReLU neural network estimator, we derive non-asymptotic bounds for both its conditional mean and variance estimation, representing the first result for variance estimation using ReLU networks.
Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective
Advancing towards generalist agents necessitates the concurrent processing of multiple tasks using a unified model, thereby underscoring the growing significance of simultaneous model training on multiple downstream tasks.
Cross-modal Information Flow in Multimodal Large Language Models
While there exists a variety of studies investigating the processing of linguistic information within large language models, little is currently known about the inner working mechanism of MLLMs and how linguistic and visual information interact within these models.
Distributed Sign Momentum with Local Steps for Training Transformers
Pre-training Transformer models is resource-intensive, and recent studies have shown that sign momentum is an efficient technique for training large-scale deep learning models, particularly Transformers.
Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory
Text-to-image (T2I) diffusion models have revolutionized generative modeling by producing high-fidelity, diverse, and visually realistic images from textual prompts.
Dense ReLU Neural Networks for Temporal-spatial Model
We broaden existing theoretical findings of temporal-spatial analysis by applying them to neural networks in more general contexts and demonstrate that our proof techniques are effective for models with short-range dependence.
Mixture of Knowledge Minigraph Agents for Literature Review Generation
A novel prompt-based algorithm, the knowledge minigraph construction agent (KMCA), is designed to identify relations between concepts from academic literature and automatically constructs knowledge minigraphs.
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayesian Theory
Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings.
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
Recent years have witnessed a clear trend towards language models with an ever-increasing number of parameters, as well as the growing training overhead and memory usage.
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting
Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks.
MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router
Experimental results demonstrate that the Mixtral-8x7B model with 50% sparsity maintains 99% of the performance of the original model after the expert-wise knowledge distillation.
Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization
We address the challenge of online Reinforcement Learning from Human Feedback (RLHF) with a focus on self-rewarding alignment methods.
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces.
Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis
This technique leverages the real-time rendering performance of 3D Gaussian Splatting with rasterization and allows for differentiable optimization in real time through CUDA implementation.
Let the Code LLM Edit Itself When You Edit the Code
Simply encoding the edited subsequence and integrating it to the original KV cache meets the temporal confusion problem, leading to significantly worse performance.
Interference Cancellation Based Neural Receiver for Superimposed Pilot in Multi-Layer Transmission
In this paper, an interference cancellation based neural receiver for superimposed pilot (SIP) in multi-layer transmission is proposed, where the data and pilot are non-orthogonally superimposed in the same time-frequency resource.
Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
Data users have been endowed with the right to be forgotten of their data.
Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation
A novel data-driven method for formal verification is proposed to study complex systems operating in safety-critical domains.
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Training LLMs at this scale brings unprecedented challenges to training efficiency and stability.
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE).
Gradient-based Parameter Selection for Efficient Fine-Tuning
With the growing size of pre-trained models, full fine-tuning and storing all the parameters for various downstream tasks is costly and infeasible.
Self-Infilling Code Generation
This work introduces self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding.
Knowledge-driven Meta-learning for CSI Feedback
In this article, a knowledge-driven meta-learning approach is proposed, where the DL model initialized by the meta model obtained from meta training phase is able to achieve rapid convergence when facing a new scenario during target retraining phase.
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present.
GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video
3D human pose lifting is one of the promising research directions toward the task where both estimated pose and ground truth pose data are used for training.
Ranked #1 on
3D Human Pose Estimation
on HumanEva-I
CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension
The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity.
Numerical analysis of a multistable capsule system under the delayed feedback control with a constant delay
In this paper, we study the control of coexisting attractors in this system by using a delayed feedback controller (DFC) with a constant delay.
A Knowledge-Driven Meta-Learning Method for CSI Feedback
Recently, deep learning (DL) has been introduced to enhance CSI feedback in massive MIMO application, where the massive collected training data and lengthy training time are costly and impractical for realistic deployment.
TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World
We observe that the backdoor effect of both misclassification and the cloaking are robustly achieved in the wild when the backdoor is activated with inconspicuously natural physical triggers.
AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback
This paper is based on the background of the 2nd Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AIWork Group, where the framework of the eigenvector-based channel state information (CSI) feedback problem is firstly provided.
CASSOCK: Viable Backdoor Attacks against DNN in The Wall of Source-Specific Backdoor Defences
Compared with a representative SSBA as a baseline ($SSBA_{Base}$), $CASSOCK$-based attacks have significantly advanced the attack performance, i. e., higher ASR and lower FPR with comparable CDA (clean data accuracy).
Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures
Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumptions defined in their respective threat models.
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
Multiple datasets and open challenges for object detection have been introduced in recent years.
Ranked #1 on
Object Detection
on BigDetection val
Deep AutoAugment
In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA).
Ranked #2 on
Data Augmentation
on ImageNet
PPA: Preference Profiling Attack Against Federated Learning
By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed.
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World
The averaged ASR still remains sufficiently high to be 78% in the transfer learning attack scenarios evaluated on CenterNet.
NTD: Non-Transferability Enabled Backdoor Detection
A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model deployments.
Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory
This paper proposes a new algorithm for learning the optimal policies under a novel multi-agent predictive state representation reinforcement learning model.
GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition
Data augmentation has recently achieved considerable performance improvement for deep learning models: increased accuracy, stability, and reduced over-fitting.
Quantization Backdoors to Deep Learning Commercial Frameworks
This work reveals that the standard quantization toolkits can be abused to activate a backdoor.
Progressive Coordinate Transforms for Monocular 3D Object Detection
Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.
Video Contrastive Learning with Global Context
Our formulation is able to capture global context in a video, thus robust to temporal content change.
AI Enlightens Wireless Communication: Analyses, Solutions and Opportunities on CSI Feedback
In this paper, we give a systematic description of the 1st Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AI Work Group.
RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things
To this end, a 1-bit quantized DNN model or deep binary neural network maximizes the memory efficiency, where each parameter in a BNN model has only 1-bit.
Attention in Attention Network for Image Super-Resolution
In this work, we attempt to quantify and visualize attention mechanisms in SISR and show that not all attention modules are equally beneficial.
Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things
Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning training without accessing raw data on clients or end devices.
CrossNorm and SelfNorm for Generalization under Distribution Shifts
Can we develop new normalization methods to improve generalization robustness under distribution shifts?
Unity of Opposites: SelfNorm and CrossNorm for Model Robustness
CrossNorm exchanges styles between feature channels to perform style augmentation, diversifying the content and style mixtures.
Insight-HXMT observations of Swift J0243.6+6124: the evolution of RMS pulse fractions at super-Eddington luminosity
The results show a general trend of the pulse fraction increasing with luminosity and energy at super-critical luminosity.
High Energy Astrophysical Phenomena
A Comprehensive Study of Deep Video Action Recognition
Video action recognition is one of the representative tasks for video understanding.
AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results
Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details.
Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor. Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks.
TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking.
Target localization and proposal generation are two essential subtasks in generic visual tracking, and it is a challenge to address both the two efficiently.
Improving Semantic Segmentation via Self-Training
In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models.
ResNeSt: Split-Attention Networks
It is well known that featuremap attention and multi-path representation are important for visual recognition.
Ranked #10 on
Instance Segmentation
on COCO test-dev
(APM metric)
Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks
In particular, for vision tasks, we can always achieve a 0% FRR and FAR.
Cryptography and Security
Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization
Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+2
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
One difficulty we observe is that the noise in the stochastic momentum estimation is accumulated over time and will have delayed effects when the batch size changes.
Bag of Freebies for Training Object Detection Neural Networks
Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}.
Bag of Tricks for Image Classification with Convolutional Neural Networks
Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.
Ranked #38 on
Domain Generalization
on VizWiz-Classification
Progressive Neural Networks for Image Classification
The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images.
KASR: A Reliable and Practical Approach to Attack Surface Reduction of Commodity OS Kernels
In this paper, we propose a reliable and practical system, named KASR, which transparently reduces attack surfaces of commodity OS kernels at runtime without requiring their source code.
Cryptography and Security Operating Systems
Still Hammerable and Exploitable: on the Effectiveness of Software-only Physical Kernel Isolation
The exploit is motivated by our key observation that the modern OSes have double-owned kernel buffers (e. g., video buffers) owned concurrently by the kernel and user domains.
Cryptography and Security
Knowledge Projection for Deep Neural Networks
In this paper, we will develop a new framework for training deep neural networks on datasets with limited labeled samples using cross-network knowledge projection which is able to improve the network performance while reducing the overall computational complexity significantly.
Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation
Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model.
Ranked #6 on
Pose Estimation
on Leeds Sports Poses
Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking.
