Search Results for author:
Found 71 papers, 24 papers with code
EmojiCloud: a Tool for Emoji Cloud Visualization
This paper proposes EmojiCloud, an open-source Python-based emoji cloud visualization tool, to generate a quick and straightforward understanding of emojis from the perspective of frequency and importance.
LoongServe: Efficiently Serving Long-context Large Language Models with Elastic Sequence Parallelism
The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request.
SoK: Gradient Leakage in Federated Learning
While GIAs have demonstrated effectiveness under \emph{ideal settings and auxiliary assumptions}, their actual efficacy against \emph{practical FL systems} remains under-explored.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
Characterization of Large Language Model Development in the Datacenter
Large Language Models (LLMs) have presented impressive performance across several transformative tasks.
RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
This paper presents a robust watermark embedding scheme, named RobWE, to protect the ownership of personalized models in PFL.
Large Language Models as Agents in Two-Player Games
By formally defining the training processes of large language models (LLMs), which usually encompasses pre-training, supervised fine-tuning, and reinforcement learning with human feedback, within a single and unified machine learning paradigm, we can glean pivotal insights for advancing LLM technologies.
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.
ReFT: Reasoning with Reinforced Fine-Tuning
ReFT first warmups the model with SFT, and then employs on-line reinforcement learning, specifically the PPO algorithm in this paper, to further fine-tune the model, where an abundance of reasoning paths are automatically sampled given the question and the rewards are naturally derived from the ground-truth answers.
On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
Contemporary machine learning requires training large neural networks on massive datasets and thus faces the challenges of high computational demands.
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
TorchAudio is an open-source audio and speech processing library built for PyTorch.
BiSinger: Bilingual Singing Voice Synthesis
We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data.
SST: A Simplified Swin Transformer-based Model for Taxi Destination Prediction based on Existing Trajectory
Accurately predicting the destination of taxi trajectories can have various benefits for intelligent location-based services.
ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting
The criticality of prompt and precise traffic forecasting in optimizing traffic flow management in Intelligent Transportation Systems (ITS) has drawn substantial scholarly focus.
Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception
In this paper, we propose SCOPE, a novel collaborative perception framework that aggregates the spatio-temporal awareness characteristics across on-road agents in an end-to-end manner.
A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives
Then, to attain strong stealthiness, we incorporate Fourier Transform and Discrete Cosine Transform to mix the poisoned image and clean image in the frequency domain.
Metric-aligned Sample Selection and Critical Feature Sampling for Oriented Object Detection
First, to align the metric inconsistency between sample selection and regression loss calculation caused by fixed IoU strategy, we introduce affine transformation to evaluate the quality of samples and propose a distance-based label assignment strategy.
On the Confidence Intervals in Bioequivalence Studies
A bioequivalence study is a type of clinical trial designed to compare the biological equivalence of two different formulations of a drug.
ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-temporal Graph Attention and Bidirectional Recurrent United Neural Networks
Traffic data serves as a fundamental component in both research and applications within intelligent transportation systems.
Privacy-preserving Adversarial Facial Features
In this paper, we propose an adversarial features-based face privacy protection (AdvFace) approach to generate privacy-preserving adversarial features, which can disrupt the mapping from adversarial features to facial images to defend against reconstruction attacks.
Optimization Design for Federated Learning in Heterogeneous 6G Networks
With the rapid advancement of 5G networks, billions of smart Internet of Things (IoT) devices along with an enormous amount of data are generated at the network edge.
Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Strategy card game is a well-known genre that is demanding on the intelligent game-play and can be an ideal test-bench for AI.
Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play
Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage.
Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication
Training Graph Neural Networks (GNNs) on large graphs is challenging due to the conflict between the high memory demand and limited GPU memory.
A novel efficient Multi-view traffic-related object detection framework
With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception.
Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search
For local information exchange, a graph convolutional network (GCN) guided module is seamlessly integrated as a communication deliver between cells.
Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
Event-Based Frame Interpolation with Ad-hoc Deblurring
The performance of video frame interpolation is inherently correlated with the ability to handle motion in the input scene.
Towards Transferable Targeted Adversarial Examples
In this paper, we propose the Transferable Targeted Adversarial Attack (TTAA), which can capture the distribution information of the target class from both label-wise and feature-wise perspectives, to generate highly transferable targeted adversarial examples.
CSI-PPPNet: A One-Sided One-for-All Deep Learning Framework for Massive MIMO CSI Feedback
The CSI is compressed via linear projections at the UE, and is recovered at the BS using deep learning (DL) with plug-and-play priors (PPP).
Controllability of a Class of Swarm Signaling Networks
In this paper, we propose closed-form analytical expressions to determine the minimum number of driver nodes that is needed to control a specific class of networks.
Multimodal Graph Learning for Deepfake Detection
We evaluate the effectiveness of our method through extensive experiments on widely-used benchmarks and demonstrate that our method outperforms the state-of-the-art detectors in terms of generalization ability and robustness against unknown disturbances.
Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision
Deep learning (DL) shows its prosperity in a wide variety of fields.
TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving
In particular, TrajGen consists of the multi-modal trajectory prediction stage and the reinforcement learning based trajectory modification stage.
Generative Adversarial Exploration for Reinforcement Learning
Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel.
A Simulation Platform for Multi-tenant Machine Learning Services on Thousands of GPUs
Multi-tenant machine learning services have become emerging data-intensive workloads in data centers with heavy usage of GPU resources.
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
A unified framework named ERNIE 3. 0 was recently proposed for pre-training large-scale knowledge enhanced models and trained a model with 10 billion parameters.
Event-Based Fusion for Motion Deblurring with Cross-modal Attention
Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times.
Ranked #3 on
Deblurring
on GoPro
(using extra training data)
Superior Performance with Diversified Strategic Control in FPS Games Using General Reinforcement Learning
We provide comprehensive analysis and experiments to elaborate the effect of each component in affecting the agent performance, and demonstrate that the proposed and adopted techniques are important to achieve superior performance in general end-to-end FPS games.
Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters
Modern GPU datacenters are critical for delivering Deep Learning (DL) models and services in both the research community and industry.
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
We trained the model with 10 billion parameters on a 4TB corpus consisting of plain texts and a large-scale knowledge graph.
Towards Distraction-Robust Active Visual Tracking
In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance.
ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems
MLOps is about taking experimental ML models to production, i. e., serving the models to actual users.
FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning
The results demonstrate its effectiveness and superior performance compared to the state-of-the-art Byzantine-robust schemes in defending against typical data poisoning and model poisoning attacks under practical Non-IID data distributions.
Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
In principle, the feature modeling scheme is carried out in a depth-sensitive attention module, which leads to the RGB feature enhancement as well as the background distraction reduction by capturing the depth geometry prior.
Self-Renormalization of Quasi-Light-Front Correlators on the Lattice
In applying large-momentum effective theory, renormalization of the Euclidean correlators in lattice regularization is a challenge due to linear divergences in the self-energy of Wilson lines.
High Energy Physics - Lattice High Energy Physics - Phenomenology
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
We show that with orders of less computation scale, a faithful reimplementation of AlphaStar's methods can not succeed and the proposed techniques are necessary to ensure TStarBot-X's competitive performance.
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems.
An Autonomous Approach to Measure Social Distances and Hygienic Practices during COVID-19 Pandemic in Public Open Spaces
Coronavirus has been spreading around the world since the end of 2019.
A Effective Carrier Phase Recovery Method in Tigth Time-Packing Fast than Nyquist Optical Communication System
We propose a new scheme that combines polybinary transformaton and corrected-BPS to compensate noise for PDM-FTN-QPSK when its accelerated factor is 0. 5, which has 3. 3 dB OSNR gain when phase noise is 800 kHz.
Identification of splicing edges in tampered image based on Dichromatic Reflection Model
Therefore we present a novel optic-physical method to discriminate splicing edges from natural edges in a tampered image.
Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
To satisfy the stringent requirements on computational resources in the field of real-time semantic segmentation, most approaches focus on the hand-crafted design of light-weight segmentation networks.
Neural Architecture Search
Real-Time Semantic Segmentation
+1
Measuring the Utilization of Public Open Spaces by Deep Learning: a Benchmark Study at the Detroit Riverfront
It is appealing to make use of surveillance cameras and to extract user-related information through computer vision.
Graph-guided Architecture Search for Real-time Semantic Segmentation
Unlike previous works that use a simplified search space and stack a repeatable cell to form a network, we introduce a novel search mechanism with new search space where a lightweight model can be effectively explored through the cell-level diversity and latencyoriented constraint.
Composing Knowledge Graph Embeddings via Word Embeddings
As $(\mathbf{h},\mathbf{r},\mathbf{t})$ is learned from the existing facts within a knowledge graph, these representations can not be used to detect unknown facts (if the entities or relations never occur in the knowledge graph).
Arena: a toolkit for Multi-Agent Reinforcement Learning
We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research.
OVSNet : Towards One-Pass Real-Time Video Object Segmentation
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames.
AD-VAT: An Asymmetric Dueling mechanism for learning Visual Active Tracking
In AD-VAT, both the tracker and the target are approximated by end-to-end neural networks, and are trained via RL in a dueling/competitive manner: i. e., the tracker intends to lockup the target, while the target tries to escape from the tracker.
Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes
To address this problem, we propose a communication backend named GradientFlow for distributed DNN training, and employ a set of network optimization techniques.
Distributed, Parallel, and Cluster Computing
Exponentially Weighted Imitation Learning for Batched Historical Data
We consider deep policy learning with only batched historical trajectories.
Salience Biased Loss for Object Detection in Aerial Images
Experimental results show our proposed loss function with the RetinaNet architecture outperformed other state-of-art object detection models by at least 4. 31 mAP, and RetinaNet by 2. 26 mAP with the same inference speed of RetinaNet.
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely.
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.
End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning
We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training.
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
Specifically, we find that a large class of primal and primal-dual operator splitting algorithms are all special cases of VMOR-HPE.
Tagging like Humans: Diverse and Distinct Image Annotation
In D2IA, we generate a relevant and distinct tag subset, in which the tags are relevant to the image contents and semantically distinct to each other, using sequential sampling from a determinantal point process (DPP) model.
PARAMETRIZED DEEP Q-NETWORKS LEARNING: PLAYING ONLINE BATTLE ARENA WITH DISCRETE-CONTINUOUS HYBRID ACTION SPACE
Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space.
Image Matters: Visually modeling user behaviors using Advanced Model Server
So we propose to model user preference jointly with user behavior ID features and behavior images.
End-to-end Active Object Tracking via Reinforcement Learning
We study active object tracking, where a tracker takes as input the visual observation (i. e., frame sequence) and produces the camera control signal (e. g., move forward, turn left, etc.).
Fast Segmentation of Left Ventricle in CT Images by Explicit Shape Regression using Random Pixel Difference Features
On a dataset consisting of 139 CT volumes, a 5-fold cross validation shows the segmentation error is $1. 21 \pm 0. 11$ for LV endocardium and $1. 23 \pm 0. 11$ millimeters for epicardium.
Globally Tuned Cascade Pose Regression via Back Propagation with Application in 2D Face Pose Estimation and Heart Segmentation in 3D CT Images
We empirically show that global training with BP outperforms layer-wise (pre-)training.
