Search Results for author:
Found 40 papers, 7 papers with code
Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning
In this paper, we propose a targeted instruction data generation framework named DFTG that tailored to the hallucination specificity of different models.
Implicit Image-to-Image Schrodinger Bridge for CT Super-Resolution and Denoising
As a promising alternative, the Image-to-Image Schr\"odinger Bridge (I2SB) initializes the generative process from corrupted images and integrates training techniques from conditional diffusion models.
A Safe Reinforcement Learning Algorithm for Supervisory Control of Power Plants
In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the control scheme accordingly.
Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs
To address this issue, We propose a language-assisted diagnostic method that uses texts instead of images to diagnose bugs in vision models based on multi-modal models (eg CLIP).
Reconstructing Objects in-the-wild for Realistic Sensor Simulation
In this work, we present NeuSim, a novel approach that estimates accurate geometry and realistic appearance from sparse in-the-wild data captured at distance and at limited viewpoints.
Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
Learning world models can teach an agent how the world works in an unsupervised manner.
Skywork: A More Open Bilingual Foundation Model
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3. 2 trillion tokens drawn from both English and Chinese texts.
SkyMath: Technical Report
Large language models (LLMs) have shown great potential to solve varieties of natural language processing (NLP) tasks, including mathematical reasoning.
Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacy
Federated learning (FL) is designed to preserve data privacy during model training, where the data remains on the client side (i. e., IoT devices), and only model updates of clients are shared iteratively for collaborative learning.
Rethinking Closed-loop Training for Autonomous Driving
Recent advances in high-fidelity simulators have enabled closed-loop training of autonomous driving agents, potentially solving the distribution shift in training v. s.
Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber
This paper first presents experimental analyses revealing that the existing biased models overfit to bias-conflicting samples in the training data, which negatively impacts the debiasing performance of the target models.
Comparative Evaluation of Data Decoupling Techniques for Federated Machine Learning with Database as a Service
To evaluate this approach, the authors develop a framework called Data-Decoupling Federated Learning (DDFL) and compare it with state-of-the-art FL systems that tightly couple data management and computation.
DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
Deep learning based PET image reconstruction methods have achieved promising results recently.
STPDnet: Spatial-temporal convolutional primal dual network for dynamic PET image reconstruction
Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame.
LMPDNet: TOF-PET list-mode image reconstruction using model-based deep learning method
Additionally, we compare the spatial and temporal consumption of list-mode data and sinogram data in model-based deep learning methods, demonstrating the superiority of list-mode data in model-based TOF-PET reconstruction.
FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications
Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes.
TransEM:Residual Swin-Transformer based regularized PET image reconstruction
Positron emission tomography(PET) image reconstruction is an ill-posed inverse problem and suffers from high level of noise due to limited counts received.
Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy
Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect privacy in comparison with the traditional centralized learning paradigm.
When Creators Meet the Metaverse: A Survey on Computational Arts
The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity.
Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data
Deep network models perform excellently on In-Distribution (ID) data, but can significantly fail on Out-Of-Distribution (OOD) data.
Hybrid Local SGD for Federated Learning with Heterogeneous Communications
Communication is a key bottleneck in federated learning where a large number of edge devices collaboratively learn a model under the orchestration of a central server without sharing their own training data.
PLUMENet: Efficient 3D Object Detection from Stereo Images
In this paper we propose a model that unifies these two tasks and performs them in the same metric space.
Multi-Task Multi-Sensor Fusion for 3D Object Detection
In this paper we propose to exploit multiple related tasks for accurate multi-sensor 3D object detection.
Ranked #13 on
3D Object Detection
on KITTI Cars Easy
StrObe: Streaming Object Detection from LiDAR Packets
In this paper we propose StrObe, a novel approach that minimizes latency by ingesting LiDAR packets and emitting a stream of detections without waiting for the full sweep to be built.
Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing
Graph classification has practical applications in diverse fields.
Trading Data For Learning: Incentive Mechanism For On-Device Federated Learning
Federated Learning rests on the notion of training a global model distributedly on various devices.
Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization
Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost.
Learning Lane Graph Representations for Motion Forecasting
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions.
MultiXNet: Multiclass Multistage Multimodal Motion Prediction
One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future.
PnPNet: End-to-End Perception and Prediction with Tracking in the Loop
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles.
Concentrated Differentially Private and Utility Preserving Federated Learning
Federated learning is a machine learning setting where a set of edge devices collaboratively train a model under the orchestration of a central server without sharing their local data.
Differentially Private Federated Learning for Resource-Constrained Internet of Things
With the proliferation of smart devices having built-in sensors, Internet connectivity, and programmable computation capability in the era of Internet of things (IoT), tremendous data is being generated at the network edge.
PolyTransform: Deep Polygon Transformer for Instance Segmentation
In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods.
Ranked #1000000000 on
Instance Segmentation
on Cityscapes test
(using extra training data)
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms to enable real-time inference.
Deep Rigid Instance Scene Flow
In this paper we tackle the problem of scene flow estimation in the context of self-driving.
UPSNet: A Unified Panoptic Segmentation Network
More importantly, we introduce a parameter-free panoptic head which solves the panoptic segmentation via pixel-wise classification.
Ranked #3 on
Panoptic Segmentation
on Indian Driving Dataset
DP-ADMM: ADMM-based Distributed Learning with Differential Privacy
The goal of this paper is to provide differential privacy for ADMM-based distributed machine learning.
Structured Occlusion Coding for Robust Face Recognition
We propose the structured occlusion coding (SOC) to address occlusion problems.
Determining Points on Handwritten Mathematical Symbols
In a variety of applications, such as handwritten mathematics and diagram labelling, it is common to have symbols of many different sizes in use and for the writing not to follow simple baselines.
