Search Results for author:
Found 83 papers, 37 papers with code
Fast and Accurate Power Load Data Completion via Regularization-optimized Low-Rank Factorization
Low-rank representation learning has emerged as a powerful tool for recovering missing values in power load data due to its ability to exploit the inherent low-dimensional structures of spatiotemporal measurements.
A PID-Controlled Tensor Wheel Decomposition Model for Dynamic Link Prediction
Link prediction in dynamic networks remains a fundamental challenge in network science, requiring the inference of potential interactions and their evolving strengths through spatiotemporal pattern analysis.
OPAL: Visibility-aware LiDAR-to-OpenStreetMap Place Recognition via Adaptive Radial Fusion
LiDAR place recognition is a critical capability for autonomous navigation and cross-modal localization in large-scale outdoor environments.
A Call for New Recipes to Enhance Spatial Reasoning in MLLMs
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks.
Hysteresis-Aware Neural Network Modeling and Whole-Body Reinforcement Learning Control of Soft Robots
In this study, we present a soft robotic system designed for surgical applications and propose a hysteresis-aware whole-body neural network model that accurately captures and predicts the soft robot's whole-body motion, including its hysteretic behavior.
BitNet b1.58 2B4T Technical Report
We introduce BitNet b1. 58 2B4T, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale.
RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning
Moreover, we propose a novel neural network, RADLER, leveraging the effectiveness of contrastive self-supervised learning (SSL) and semantic 3D city models to enhance radar object detection of pedestrians, cyclists, and cars.
Reconstructing Humans with a Biomechanically Accurate Skeleton
In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model.
Enhancing Multi-modal Models with Heterogeneous MoE Adapters for Fine-tuning
Multi-modal models excel in cross-modal tasks but are computationally expensive due to their billions of parameters.
SparseAlign: A Fully Sparse Framework for Cooperative Object Detection
In this work, we design a fully sparse framework, SparseAlign, with three key features: an enhanced sparse 3D backbone, a query-based temporal context learning module, and a robust detection head specially tailored for sparse features.
MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups.
L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery
To overcome this, we first construct XA-L&RSI dataset, which encompasses approximately $110, 000$ remote sensing submaps and $13, 000$ LiDAR point cloud submaps captured in urban scenes, and propose a novel method, L2RSI, for cross-view LiDAR place recognition using high-resolution Remote Sensing Imagery.
CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving
By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation within 3D space, facilitating a more precise representation of dynamic scenes.
CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation
The construction of interleaved multimodal multi-step reasoning chains, which utilize critical visual region tokens, extracted from intermediate reasoning steps, as supervisory signals.
EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration
Large language models (LLMs) are increasingly leveraged as foundational backbones in the development of advanced recommender systems, offering enhanced capabilities through their extensive knowledge and reasoning.
FacaDiffy: Inpainting Unseen Facade Parts Using Diffusion Models
To address this challenge, we introduce FacaDiffy, a novel method for inpainting unseen facade parts by completing conflict maps with a personalized Stable Diffusion model.
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
The advent of 1-bit large language models (LLMs), led by BitNet b1. 58, has spurred interest in ternary LLMs.
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
Ultimately, MVoT establishes new possibilities for complex reasoning tasks where visual thinking can effectively complement verbal reasoning.
Semantic Residual for Multimodal Unified Discrete Representation
Recent research in the domain of multimodal unified representations predominantly employs codebook as representation forms, utilizing Vector Quantization(VQ) for quantization, yet there has been insufficient exploration of other quantization representation forms.
UniLoc: Towards Universal Place Recognition Using Any Single Modality
To date, most place recognition methods focus on single-modality retrieval.
TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes
To overcome the lack of large-scale real-world intersection datasets, we introduce Carla Intersection, a new simulated dataset with 75 urban and rural intersections in Carla.
SADG: Segment Any Dynamic Gaussian Without Object Trackers
We introduce SADG, Segment Any Dynamic Gaussian Without Object Trackers, a novel approach that combines dynamic Gaussian Splatting representation and semantic information without reliance on object IDs.
SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms
The human brain receives nutrients and oxygen through an intricate network of blood vessels.
ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset
Facade semantic segmentation is a long-standing challenge in photogrammetry and computer vision.
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs
Recent advances in 1-bit Large Language Models (LLMs), such as BitNet and BitNet b1. 58, present a promising approach to enhancing the efficiency of LLMs in terms of speed and energy consumption.
CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays
Existing rhetorical understanding and generation datasets or corpora primarily focus on single coarse-grained categories or fine-grained categories, neglecting the common interrelations between different rhetorical devices by treating them as independent sub-tasks.
World-Grounded Human Motion Recovery via Gravity-View Coordinates
Instead, we propose estimating human poses in a novel Gravity-View (GV) coordinate system, which is defined by the world gravity and the camera view direction.
PSLF: A PID Controller-incorporated Second-order Latent Factor Analysis Model for Recommender System
A second-order-based latent factor (SLF) analysis model demonstrates superior performance in graph representation learning, particularly for high-dimensional and incomplete (HDI) interaction data, by incorporating the curvature information of the loss landscape.
L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection
However, the fusion of LiDAR and 4D radar is challenging because they differ significantly in terms of data quality and the degree of degradation in adverse weather.
Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection
The core concept is the design of the coarse-to-fine fusion module, denoted as the cross-modality adaptive feature refinement (CAFR) module.
Ranked #1 on
Object Detection
on PKU-DDD17-Car
Gap Completion in Point Cloud Scene occluded by Vehicles using SGC-Net
In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion.
Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning
This paper introduces BI-Directional DEliberation Reasoning (BIDDER), a novel reasoning approach to enhance the decision rationality of language models.
TARGO: Benchmarking Target-driven Object Grasping under Occlusions
3) We also generate a large-scale training dataset via a scalable pipeline, which can be used to boost the performance of grasping under occlusion and generalized to the real world.
ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling
Generative retrieval, which has demonstrated effectiveness in text-to-text retrieval, utilizes a sequence-to-sequence model to directly generate candidate identifiers based on natural language queries.
EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration
Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem.
Meta Reasoning for Large Language Models
MRP represents a significant advancement in enabling LLMs to identify cognitive challenges across problems and leverage benefits across different reasoning approaches, enhancing their ability to handle diverse and complex problem domains efficiently.
Localizing Events in Videos with Multimodal Queries
Localizing events in videos based on semantic queries is a pivotal task in video understanding, with the growing significance of user-oriented applications like video search.
Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks.
LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models
This paper presents a comprehensive survey of the current status and opportunities for Large Language Models (LLMs) in strategic reasoning, a sophisticated form of reasoning that necessitates understanding and predicting adversary actions in multi-agent settings while adjusting strategies accordingly.
VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition
To tackle this issue, we propose Voxel-Cross-Pixel (VXP), a novel camera-to-LiDAR place recognition framework that enforces local similarities in a self-supervised manner and effectively brings global context from images and LiDAR scans into a shared feature space.
Enhancing Multimodal Unified Representations for Cross Modal Generalization
To enhance the interpretability of multimodal unified representations, many studies have focused on discrete unified representations.
GS-EMA: Integrating Gradient Surgery Exponential Moving Average with Boundary-Aware Contrastive Learning for Enhanced Domain Generalization in Aneurysm Segmentation
The automated segmentation of cerebral aneurysms is pivotal for accurate diagnosis and treatment planning.
Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning
Unsupervised domain adaptation (UDA) aims to align the labelled source distribution with the unlabelled target distribution to obtain domain-invariant predictive models.
K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning
LLMs and LLM agents often struggle with strategic reasoning due to the absence of a reasoning framework that enables them to dynamically infer others' perspectives and adapt to changing environments.
Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding
Thus, to address this issue and enhance model performance on new scenes, we explore the TVG task in an unsupervised domain adaptation (UDA) setting across scenes for the first time, where the video-query pairs in the source scene (domain) are labeled with temporal boundaries, while those in the target scene are not.
StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
Moreover, existing SVS methods encounter a decline in the quality of synthesized singing voices in OOD scenarios, as they rest upon the assumption that the target vocal attributes are discernible during the training phase.
Text2Loc: 3D Point Cloud Localization from Natural Language
We tackle the problem of 3D point cloud localization based on a few natural linguistic descriptions and introduce a novel neural network, Text2Loc, that fully interprets the semantic relationship between points and text.
Ranked #2 on
Visual Place Recognition
on KITTI360pose
Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI
In response, we introduce HybridVNet, a novel architecture for direct image-to-mesh extraction seamlessly integrating standard convolutional neural networks with graph convolutions, which we prove can efficiently handle surface and volumetric meshes by encoding them as graph structures.
Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks
This mechanism leverages audio and visual modalities as soft prompts to dynamically adjust the parameters of pre-trained models based on the current multi-modal input features.
ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents
This paper introduces Alympics (Olympics for Agents), a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research.
EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation
In this paper, we propose a new framework called Evaluation-guided Iterative Plan Extraction for long-form narrative text generation (EIPE-text), which extracts plans from the corpus of narratives and utilizes the extracted plans to construct a better planner.
SCP: Scene Completion Pre-training for 3D Object Detection
In this paper, we propose a Scene Completion Pre-training (SCP) method to enhance the performance of 3D object detectors with less labeled data.
Learned Local Attention Maps for Synthesising Vessel Segmentations
We present an encoder-decoder model for synthesising segmentations of the main cerebral arteries in the circle of Willis (CoW) from only T2 MRI.
Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels
Accurate segmentation of brain vessels is crucial for cerebrovascular disease diagnosis and treatment.
Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs
We develop two new benchmark HTKG datasets, i. e., Wiki-hy and YAGO-hy, and propose an HTKG reasoning model that efficiently models hyper-relational temporal facts.
Assessing Phrase Break of ESL Speech with Pre-trained Language Models and Large Language Models
To leverage NLP models, speech input is first force-aligned with texts, and then pre-processed into a token sequence, including words and phrase break information.
Smart Word Suggestions for Writing Assistance
The training dataset comprises over 3. 7 million sentences and 12. 7 million suggestions generated through rules.
Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Large language models (LLMs) demonstrate impressive multilingual capability, but their performance varies substantially across different languages.
Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks
To this end, we leverage laser physics and 3D building model priors to probabilistically identify model conflicts.
Low-code LLM: Graphical User Interface over Large Language Models
By introducing this framework, we aim to bridge the gap between humans and LLMs, enabling more effective and efficient utilization of LLMs for complex tasks.
TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs
On the other hand, there are also many existing models and systems (symbolic-based or neural-based) that can do some domain-specific tasks very well.
High-throughput 3DRA segmentation of brain vasculature and aneurysms using deep learning
Results:On the internal clinical dataset, our method consistently outperformed several state-of-the-art approaches for vessel and aneurysm segmentation, achieving an average Dice score of 0. 81 (0. 15 higher than nnUNet) and an average surface-to-surface error of 0. 20 mm (less than the in-plane resolution (0. 35 mm/pixel)) for aneurysm segmentation; and an average Dice score of 0. 91 and average surface-to-surface error of 0. 25 mm for vessel segmentation.
Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology
Here, we propose a new framework for gene discovery entitled Unsupervised Phenotype Ensembles (UPE).
Extensible Prompts for Language Models on Zero-shot Language Style Customization
We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL).
Joint segmentation and discontinuity-preserving deformable registration: Application to cardiac cine-MR images
In such scenarios, enforcing smooth, globally continuous deformation fields leads to incorrect/implausible registration results.
CASSPR: Cross Attention Single Scan Place Recognition
CASSPR uses queries from one branch to try to match structures in the other branch, ensuring that both extract self-contained descriptors of the point cloud (rather than one branch dominating), but using both to inform the output global descriptor of the point cloud.
Assessing Phrase Break of ESL speech with Pre-trained Language Models
The token sequence is then fed into the pre-training and fine-tuning pipeline.
Video-Guided Curriculum Learning for Spoken Video Grounding
To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise.
A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking.
Cross-Modal Background Suppression for Audio-Visual Event Localization
Audiovisual Event (AVE) localization requires the model to jointly localize an event by observing audio and visual information.
An Approach to Mispronunciation Detection and Diagnosis with Acoustic, Phonetic and Linguistic (APL) Embeddings
These embeddings, when used as implicit phonetic supplementary information, can alleviate the data shortage of explicit phoneme annotations.
Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning
Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions.
A Deep Discontinuity-Preserving Image Registration Network
Image registration aims to establish spatial correspondence across pairs, or groups of images, and is a cornerstone of medical image computing and computer-assisted-interventions.
CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
Image registration is a fundamental building block for various applications in medical image analysis.
Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter
Traditionally, heuristic methods are used to generate candidates for large scale recommender systems.
ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net.
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors.
Ranked #5 on
3D Place Recognition
on Oxford RobotCar Dataset
(AR@1% metric)
Improving pronunciation assessment via ordinal regression with anchored reference samples
Traditional speech pronunciation assessment, based on the Goodness of Pronunciation (GOP) algorithm, has some weakness in assessing a speech utterance: 1) Phoneme GOP scores cannot be easily translated into a sentence score with a simple average for effective assessment; 2) The rank ordering information has not been well exploited in GOP scoring for delivering a robust assessment and correlate well with a human rater's evaluations.
VPC-Net: Completion of 3D Vehicles from MLS Point Clouds
Moreover, a new refiner module is also presented to preserve the vehicle details from inputs and refine the complete outputs with fine-grained information.
RealPoint3D: Point Cloud Generation from a Single Image with Complex Background
Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud.
Mixed one-bit compressive sensing with applications to overexposure correction for CT reconstruction
Aiming at overexposure correction for computed tomography (CT) reconstruction, we in this paper propose a mixed one-bit compressive sensing (M1bit-CS) to acquire information from both regular and saturated measurements.
Learning Discriminative Reconstructions for Unsupervised Outlier Removal
We study the problem of automatically removing outliers from noisy data, with application for removing outlier images from an image collection.
Sparse Projections for High-Dimensional Binary Codes
This paper addresses the problem of learning long binary codes from high-dimensional data.
