Search Results for author:
Found 76 papers, 33 papers with code
LLM-assisted Labeling Function Generation for Semantic Type Detection
One challenge in this process is the difficulty of manually writing labeling functions due to the large volume and low quality of the data lake table datasets.
BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems
Compared to single agents, multi-agent systems have higher requirements for the collaboration capabilities of language models.
GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
Pre-trained language models are increasingly being used in multi-document summarization tasks.
Test-Time Adaptation with State-Space Models
Distribution shifts between training and test data are all but inevitable over the lifecycle of a deployed model and lead to performance decay.
Domain-Aware Fine-Tuning of Foundation Models
Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains.
A Contrastive Learning Based Convolutional Neural Network for ERP Brain-Computer Interfaces
However, due to the complexity of ERP signal components, their low signal-to-noise ratio, and significant inter-subject variability, cross-subject ERP signal detection has been challenging.
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
We introduce ChatGLM, an evolving family of large language models that we have been developing over time.
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
We first show that the tree-search policy in ReST-MCTS* achieves higher accuracy compared with prior LLM reasoning baselines such as Best-of-N and Tree-of-Thought, within the same search budget.
A Blueprint Architecture of Compound AI Systems for Enterprise
Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases.
DSCA: A Digital Subtraction Angiography Sequence Dataset and Spatio-Temporal Model for Cerebral Artery Segmentation
Additionally, we propose DSANet, a spatio-temporal network for CA segmentation in DSA sequences.
Fast yet Safe: Early-Exiting with Risk Control
Scaling machine learning models significantly improves their performance.
Unified Directly Denoising for Both Variance Preserving and Variance Exploding Diffusion Models
Here, we propose a unified DDDM (uDDDM) framework that generates images in one-step/multiple steps for both Variance Preserving (VP) and Variance Exploding (VE) cases.
Directly Denoising Diffusion Models
In this paper, we present the Directly Denoising Diffusion Model (DDDM): a simple and generic approach for generating realistic images with few-step sampling, while multistep sampling is still preserved for better performance.
Palette-based Color Transfer between Images
As an important subtopic of image enhancement, color transfer aims to enhance the color scheme of a source image according to a reference one while preserving the semantic context.
ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers
3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map.
AutoRE: Document-Level Relation Extraction with Large Language Models
Large Language Models (LLMs) have demonstrated exceptional abilities in comprehending and generating text, motivating numerous researchers to utilize them for Information Extraction (IE) purposes, including Relation Extraction (RE).
VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content.
Renovating Names in Open-Vocabulary Segmentation Benchmarks
Names are essential to both human cognition and vision-language models.
MEGAnno+: A Human-LLM Collaborative Annotation System
Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks.
OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining
We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field.
Contrastive Learning of Shared Spatiotemporal EEG Representations Across Individuals for Naturalistic Neuroscience
Targeting the Electroencephalogram (EEG) technique, known for its rich spatial and temporal information, this study presents a framework for Contrastive Learning of Shared SpatioTemporal EEG Representations across individuals (CL-SSTER).
RecDCL: Dual Contrastive Learning for Recommendation
In this work, we investigate how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation.
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
Current L2I models either suffer from poor editability via text or weak alignment between the generated image and the input layout.
SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning
To bridge these gaps, we introduce SciGLM, a suite of scientific language models able to conduct college-level scientific reasoning.
Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift
Knowing if a model will generalize to data 'in the wild' is crucial for safe deployment.
Early-Exit Neural Networks with Nested Prediction Sets
These sequences are inherently nested and thus well-suited for an EENN's sequential predictions.
FactCHD: Benchmarking Fact-Conflicting Hallucination Detection
Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications.
XIMAGENET-12: An Explainable AI Benchmark Dataset for Model Robustness Evaluation
Despite the promising performance of existing visual models on public benchmarks, the critical assessment of their robustness for real-world applications remains an ongoing challenge.
DocPrompt: Large-scale continue pretrain for zero-shot and few-shot document question answering
In this paper, we propose Docprompt for document question answering tasks with powerful zero-shot and few-shot performance.
Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation
Within the context of autonomous driving, encountering unknown objects becomes inevitable during deployment in the open world.
Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review
The advent of deep learning has brought a revolutionary transformation to image denoising techniques.
Divide & Bind Your Attention for Improved Generative Semantic Nursing
To address the challenges posed by complex prompts or scenarios involving multiple entities and to achieve improved attribute binding, we propose Divide & Bind.
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization
Using the proposed masked noise encoder to randomize style and content combinations in the training set, i. e., intra-source style augmentation (ISSA) effectively increases the diversity of training data and reduces spurious correlation.
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.
Contrastive Representation Disentanglement for Clustering
We conduct a theoretical analysis of the proposed loss and highlight how it assigns different weights to negative samples during the process of disentangling the feature representation.
High Dynamic Range Imaging with Context-aware Transformer
In each Dual Transformer (DT), the global features are extracted by the window-based Transformer, while the local details are extracted using the channel attention mechanism with deformable CNNs.
Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer
In this paper, we propose a novel Denoise Transformer for real-world image denoising, which is mainly constructed with Context-aware Denoise Transformer (CADT) units and Secondary Noise Extractor (SNE) block.
MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network
Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods.
Identification of Systematic Errors of Image Classifiers on Rare Subgroups
Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data.
Learning From Yourself: A Self-Distillation Method for Fake Speech Detection
To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks.
Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
Humans no doubt use language to communicate about their emotional experiences, but does language in turn help humans understand emotions, or is language just a vehicle of communication?
Towards Multifaceted Human-Centered AI
Human-centered AI workflows involve stakeholders with multiple roles interacting with each other and automated agents to accomplish diverse tasks.
MEGAnno: Exploratory Labeling for NLP in Computational Notebooks
We present MEGAnno, a novel exploratory annotation framework designed for NLP researchers and practitioners.
GOOD: Exploring Geometric Cues for Detecting Objects in an Open World
We address the task of open-world class-agnostic object detection, i. e., detecting every object in an image by learning from a limited number of base object classes.
Ranked #1 on
Open World Object Detection
on COCO VOC to non-VOC
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e. g., full stack System-on-Chip design).
Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model
In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual language models.
Intra-Source Style Augmentation for Improved Domain Generalization
Using the proposed masked noise encoder to randomize style and content combinations in the training set, ISSA effectively increases the diversity of training data and reduces spurious correlation.
TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation.
One-Shot Synthesis of Images and Segmentation Masks
To this end, inspired by the recent architectural developments of single-image GANs, we introduce our OSMIS model which enables the synthesis of segmentation masks that are precisely aligned to the generated images in the one-shot regime.
Retinal Structure Detection in OCTA Image via Voting-based Multi-task Learning
Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making.
A Data Driven Method for Multi-step Prediction of Ship Roll Motion in High Sea States
This paper presents a novel data-driven methodology to provide a multi-step prediction of ship roll motions in high sea states.
Sparse-based Domain Adaptation Network for OCTA Image Super-Resolution Reconstruction
To be more specific, we first perform a simple degradation of the 3x3 mm2/high-resolution (HR) image to obtain the synthetic LR image.
Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap
As a rising task, panoptic segmentation is faced with challenges in both semantic segmentation and instance segmentation.
Contrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition
Contrastive learning was employed to minimize the inter-subject differences by maximizing the similarity in EEG signal representations across subjects when they received the same emotional stimuli in contrast to different ones.
BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation
The other is the content guidance bridge (CGBdg) designed for the depth map reconstruction process, which provides the content guidance learned from DSR task for MDE task.
A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators
The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads.
Annotating Columns with Pre-trained Language Models
Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information.
Ranked #1 on
Column Type Annotation
on VizNet-Sato-MultiColumn
Generating Novel Scene Compositions from Single Images and Videos
In this work, we introduce SIV-GAN, an unconditional generative model that can generate new scene compositions from a single training image or a single video clip.
MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN
Magnetic induction tomography (MIT) is an efficient solution for long-term brain disease monitoring, which focuses on reconstructing bio-impedance distribution inside the human brain using non-intrusive electromagnetic fields.
$\rm ^{83}Rb$/$\rm ^{83m}Kr$ production and cross-section measurement with 3.4 MeV and 20 MeV proton beams
$\rm ^{83m}Kr$, with a short lifetime, is an ideal calibration source for liquid xenon or liquid argon detectors.
Nuclear Experiment Instrumentation and Detectors
You Only Need Adversarial Supervision for Semantic Image Synthesis
By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, we are able to synthesize images of higher fidelity with better alignment to their input label maps, making the use of the perceptual loss superfluous.
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
The goal of this paper is to resolve the identified issues of HB in order to provide calibrated confidence estimates using only a small holdout calibration dataset for bin optimization while preserving multi-class ranking accuracy.
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
We refine previous investigations of this failure at anomaly detection for invertible generative networks and provide a clear explanation of it as a combination of model bias and domain prior: Convolutional networks learn similar low-level feature distributions when trained on any natural image dataset and these low-level features dominate the likelihood.
MGA: Momentum Gradient Attack on Network
The adversarial attack methods based on gradient information can adequately find the perturbations, that is, the combinations of rewired links, thereby reducing the effectiveness of the deep learning model based graph embedding algorithms, but it is also easy to fall into a local optimum.
Social and Information Networks
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks.
Sato: Contextual Semantic Type Detection in Tables
Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search.
Ranked #2 on
Column Type Annotation
on VizNet-Sato-MultiColumn
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
PolSAR Image Classification based on Polarimetric Scattering Coding and Sparse Support Matrix Machine
In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine.
Unsupervised Euclidean Distance Attack on Network Embedding
Since a large number of downstream network algorithms, such as community detection and node classification, rely on the Euclidean distance between nodes to evaluate the similarity between them in the embedding space, EDA can be considered as a universal attack on a variety of network algorithms.
Social and Information Networks Physics and Society
E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction
Predicting the potential relations between nodes in networks, known as link prediction, has long been a challenge in network science.
Progressive Augmentation of GANs
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well.
Ranked #3 on
Image Generation
on CelebA-HQ 128x128
PA-GAN: Improving GAN Training by Progressive Augmentation
Despite recent progress, Generative Adversarial Networks (GANs) still suffer from training instability, requiring careful consideration of architecture design choices and hyper-parameter tuning.
Polarimetric Convolutional Network for PolSAR Image Classification
Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information.
Partial Labeled Gastric Tumor Segmentation via patch-based Reiterative Learning
Gastric cancer is the second leading cause of cancer-related deaths worldwide, and the major hurdle in biomedical image analysis is the determination of the cancer extent.
Principled Evaluation of Differentially Private Algorithms using DPBench
Differential privacy has become the dominant standard in the research community for strong privacy protection.
Databases Cryptography and Security
Multiple Instance Learning on Structured Data
Ignoring this structure information limits the performance of existing MIL algorithms.
