Search Results for author:
Found 64 papers, 25 papers with code
Mixture of Experts for Node Classification
Nodes in the real-world graphs exhibit diverse patterns in numerous aspects, such as degree and homophily.
HyQE: Ranking Contexts with Hypothetical Query Embeddings
A standard approach is to measure this relevance through the similarity between contexts and queries in the embedding space.
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
Large language models (LLMs) have demonstrated remarkable capabilities; however, the optimization of their prompts has historically prioritized performance metrics at the expense of crucial safety and security considerations.
Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models
Large language models (LLMs) are proficient in capturing factual knowledge across various domains.
Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowledge corpus to complement the parametric knowledge in LMs provides a tangible solution to these problems.
SeMv-3D: Towards Semantic and Mutil-view Consistency simultaneously for General Text-to-3D Generation with Triplane Priors
Recent advancements in generic 3D content generation from text prompts have been remarkable by fine-tuning text-to-image diffusion (T2I) models or employing these T2I models as priors to learn a general text-to-3D model.
LEGO: Self-Supervised Representation Learning for Scene Text Images
To tackle this problem, a highly promising approach is to utilize massive amounts of unlabeled real data for self-supervised training, which has been widely proven effective in many NLP and CV tasks.
CAMAv2: A Vision-Centric Approach for Static Map Element Annotation
Compared with the original nuScenes static map element, our CAMAv2 annotations achieve lower reprojection errors (e. g., 4. 96 vs. 8. 03 pixels).
Revolutionizing Urban Safety Perception Assessments: Integrating Multimodal Large Language Models with Street View Images
However, achieving this goal often requires extensive human annotation to train safety ranking models, and the architectural differences between cities hinder the transferability of these models.
Lateralization LoRA: Interleaved Instruction Tuning with Modality-Specialized Adaptations
Lateralization LoRA employs a hybrid approach, combining the traditional linear LoRA and a Convolutional LoRA for generating text and images, enabling the generation of high-quality text and images by leveraging modality-specific structures and parameter sets.
DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming
Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layouts typical of document images.
Holistic Evaluation for Interleaved Text-and-Image Generation
InterleavedBench features a rich array of tasks to cover diverse real-world use cases.
DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks
This underscores the potential of DocRes across a broader spectrum of document image restoration tasks.
GOLD: Geometry Problem Solver with Natural Language Description
Addressing the challenge of automated geometry math problem-solving in artificial intelligence (AI) involves understanding multi-modal information and mathematics.
Ranked #1 on
Mathematical Reasoning
on UniGeo
Test-Time Training on Graphs with Large Language Models (LLMs)
Graph Neural Networks have demonstrated great success in various fields of multimedia.
VRSO: Visual-Centric Reconstruction for Static Object Annotation
As a part of the perception results of intelligent driving systems, static object detection (SOD) in 3D space provides crucial cues for driving environment understanding.
SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models
Motivated by this gap, we introduce a novel UQ method, sampling with perturbation for UQ (SPUQ), designed to tackle both aleatoric and epistemic uncertainties.
Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods
Uncertainty estimation is a crucial aspect of deploying dependable deep learning models in safety-critical systems.
PhaseEvo: Towards Unified In-Context Prompt Optimization for Large Language Models
Crafting an ideal prompt for Large Language Models (LLMs) is a challenging task that demands significant resources and expert human input.
GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving
To address this gap, we introduce the GeoEval benchmark, a comprehensive collection that includes a main subset of 2, 000 problems, a 750 problems subset focusing on backward reasoning, an augmented subset of 2, 000 problems, and a hard subset of 300 problems.
GAPS: Geometry-Aware Problem Solver
By leveraging these improvements, GAPS showcases remarkable performance in resolving geometry math problems.
Ranked #1 on
Mathematical Reasoning
on UniGeo (PRV)
GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning
Specifically, we utilize constrained optimization to enforce local fairness on the client side and adopt a fairness-aware clustering-based aggregation on the server to further ensure the global model fairness across different sensitive groups while maintaining high utility.
DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models
Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge.
UPOCR: Towards Unified Pixel-Level OCR Interface
Without bells and whistles, the experimental results showcase that the proposed method can simultaneously achieve state-of-the-art performance on three tasks with a unified single model, which provides valuable strategies and insights for future research on generalist OCR models.
Advancing Urban Renewal: An Automated Approach to Generating Historical Arcade Facades with Stable Diffusion Models
Urban renewal and transformation processes necessitate the preservation of the historical urban fabric, particularly in districts known for their architectural and historical significance.
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models
The performance of optical character recognition (OCR) heavily relies on document image quality, which is crucial for automatic document processing and document intelligence.
On the Quantification of Image Reconstruction Uncertainty without Training Data
This, in turn, facilitates a probabilistic interpretation of observational data for decision-making.
SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency
Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs).
A Vision-Centric Approach for Static Map Element Annotation
The recent development of online static map element (a. k. a.
Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning
Finally, the model is refined with the only input of reliable normal nodes and learns a more accurate estimate of normality so that anomalous nodes can be more easily distinguished.
Can Programming Languages Boost Each Other via Instruction Tuning?
Results demonstrate that programming languages can significantly improve each other.
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer
To this end, we introduce a new model named Explicit Synergy-based Text Spotting Transformer framework (ESTextSpotter), which achieves explicit synergy by modeling discriminative and interactive features for text detection and recognition within a single decoder.
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation.
RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation
This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces.
DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures
Furthermore, considering the importance of fine-grained elements in document images, we present a details recurrent refinement module to enhance the output in a high-resolution space.
M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion.
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
In this paper, we seek to reconcile utility and privacy in FL by proposing a user-configurable privacy defense, RecUP-FL, that can better focus on the user-specified sensitive attributes while obtaining significant improvements in utility over traditional defenses.
Speech Privacy Leakage from Shared Gradients in Distributed Learning
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis.
SPTS v2: Single-Point Scene Text Spotting
Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations.
Ranked #15 on
Text Spotting
on ICDAR 2015
M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion.
Towards Accurate Ground Plane Normal Estimation from Ego-Motion
In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles.
Accelerating Inverse Learning via Intelligent Localization with Exploratory Sampling
In the scope of "AI for Science", solving inverse problems is a longstanding challenge in materials and drug discovery, where the goal is to determine the hidden structures given a set of desirable properties.
ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler
Numerical reasoning over text is a challenging task of Artificial Intelligence (AI), requiring reading comprehension and numerical reasoning abilities.
Ranked #1 on
Math Word Problem Solving
on MathQA
Atomic structure generation from reconstructing structural fingerprints
These methods would help identify or, in the case of generative models, even create novel crystal structures of materials with a set of specified functional properties to then be synthesized or isolated in the laboratory.
Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild
To address this issue, we propose a novel approach called Marior (Margin Removal and \Iterative Content Rectification).
Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage
Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.
Road-aware Monocular Structure from Motion and Homography Estimation
The Depth-CNN and Pose-CNN estimate dense depth map and ego-motion respectively, solving SFM, while the Pose-CNN and Ground-CNN followed by a homography layer solve the ground plane estimation problem.
SPTS: Single-Point Text Spotting
For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance.
Ranked #3 on
Text Spotting
on SCUT-CTW1500
Simulation Intelligence: Towards a New Generation of Scientific Methods
We present the "Nine Motifs of Simulation Intelligence", a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence.
On the Stochastic Stability of Deep Markov Models
Deep Markov models (DMM) are generative models that are scalable and expressive generalization of Markov models for representation, learning, and inference problems.
AutoNF: Automated Architecture Optimization of Normalizing Flows Using a Mixture Distribution Formulation
Although various flow models based on different transformations have been proposed, there still lacks a quantitative analysis of performance-cost trade-offs between different flows as well as a systematic way of constructing the best flow architecture.
Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updates
Federated Learning (FL) enables multiple distributed clients (e. g., mobile devices) to collaboratively train a centralized model while keeping the training data locally on the client.
Inverse design of two-dimensional materials with invertible neural networks
The ability to readily design novel materials with chosen functional properties on-demand represents a next frontier in materials discovery.
Deep Online Correction for Monocular Visual Odometry
Second, the poses predicted by CNNs are further improved by minimizing photometric errors via gradient updates of poses during inference phases.
A Hybrid Gradient Method to Designing Bayesian Experiments for Implicit Models
However, the approach in Kleinegesse et al., 2020 requires a pathwise sampling path to compute the gradient of the MI lower bound with respect to the design variables, and such a pathwise sampling path is usually inaccessible for implicit models.
A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Models
However, the approach requires a sampling path to compute the pathwise gradient of the MI lower bound with respect to the design variables, and such a pathwise gradient is usually inaccessible for implicit models.
Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution
Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and intelligent education.
Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
In this paper, we propose a thermodynamic consistent neural network (TCNN) approach to build a data-driven model of the TSR with sparse experimental data.
Scalable Deep-Learning-Accelerated Topology Optimization for Additively Manufactured Materials
Unlike the existing studies of DL for TO, our framework accelerates TO by learning the iterative history data and simultaneously training on the mapping between the given design and its gradient.
A Novel Evolution Strategy with Directional Gaussian Smoothing for Blackbox Optimization
Standard ES methods with $d$-dimensional Gaussian smoothing suffer from the curse of dimensionality due to the high variance of Monte Carlo (MC) based gradient estimators.
Robust data-driven approach for predicting the configurational energy of high entropy alloys
In this study, a robust data-driven framework based on Bayesian approaches is proposed and demonstrated on the accurate and efficient prediction of configurational energy of high entropy alloys.
Learning nonlinear level sets for dimensionality reduction in function approximation
We developed a Nonlinear Level-set Learning (NLL) method for dimensionality reduction in high-dimensional function approximation with small data.
Functional Analysis
PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction.
Power-Law Graph Cuts
Despite strong performance for a number of clustering tasks, spectral graph cut algorithms still suffer from several limitations: first, they require the number of clusters to be known in advance, but this information is often unknown a priori; second, they tend to produce clusters with uniform sizes.
