Search Results for author:
Found 91 papers, 38 papers with code
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs).
Conversation- and Tree-Structure Losses for Dialogue Disentanglement
When multiple conversations occur simultaneously, a listener must decide which conversation each utterance is part of in order to interpret and respond to it appropriately.
Expanding Training Data for Endoscopic Phenotyping of Eosinophilic Esophagitis
Eosinophilic esophagitis (EoE) is a chronic esophageal disorder marked by eosinophil-dominated inflammation.
Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision
The image compression model has long struggled with adaptability and generalization, as the decoded bitstream typically serves only human or machine needs and fails to preserve information for unseen visual tasks.
Prism: Mining Task-aware Domains in Non-i.i.d. IMU Data for Flexible User Perception
To achieve uncontrolled online prediction on mobile devices, referred to as the flexible user perception (FUP) problem, is attractive but hard.
GloFinder: AI-empowered QuPath Plugin for WSI-level Glomerular Detection, Visualization, and Curation
Artificial intelligence (AI) has demonstrated significant success in automating the detection of glomeruli, the key functional units of the kidney, from whole slide images (WSIs) in kidney pathology.
Glo-In-One-v2: Holistic Identification of Glomerular Cells, Tissues, and Lesions in Human and Mouse Histopathology
In this study, we leverage the Glo-In-One toolkit to version 2 with fine-grained segmentation capabilities, curating 14 distinct labels for tissue regions, cells, and lesions across a dataset of 23, 529 annotated glomeruli across human and mouse histopathology data.
How Good Are We? Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment
This study establishes a benchmark for the development and deployment of cell vision foundation models tailored for real-world data applications.
LLM Unlearning via Loss Adjustment with Only Forget Data
Existing approaches to LLM unlearning often rely on retain data or a reference LLM, yet they struggle to adequately balance unlearning performance with overall model utility.
Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content.
Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology
Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology.
GLAM: Glomeruli Segmentation for Human Pathological Lesions using Adapted Mouse Model
To answer this question, we introduced GLAM, a deep learning study for fine-grained segmentation of human kidney lesions using a mouse model, addressing mouse-to-human transfer learning, by evaluating different learning strategies for segmenting human pathological lesions using zero-shot transfer learning and hybrid learning by leveraging mouse samples.
Dataset Distillation in Medical Imaging: A Feasibility Study
Our extensive experiments across multiple medical datasets reveal that data distillation can significantly reduce dataset size while maintaining comparable model performance to that achieved with the full dataset, suggesting that a small, representative sample of images can serve as a reliable indicator of distillation success.
PFPs: Prompt-guided Flexible Pathological Segmentation for Diverse Potential Outcomes Using Large Vision and Language Models
The Vision Foundation Model has recently gained attention in medical image analysis.
HoloHisto: End-to-end Gigapixel WSI Segmentation with 4K Resolution Sequential Tokenization
In this paper, we propose the holistic histopathology (HoloHisto) segmentation method to achieve end-to-end segmentation on gigapixel WSIs, whose maximum resolution is above 80, 000$\times$70, 000 pixels.
HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis
Panoramic image segmentation in computational pathology presents a remarkable challenge due to the morphologically complex and variably scaled anatomy.
Weighted Circle Fusion: Ensembling Circle Representation from Different Object Detection Results
Additionally, we assess the efficiency of two annotation methods, fully manual annotation and a human-in-the-loop (HITL) approach, in labeling 200, 000 glomeruli.
mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysis
Multi-modal learning adeptly integrates visual and textual data, but its application to histopathology image and text analysis remains challenging, particularly with large, high-resolution images like gigapixel Whole Slide Images (WSIs).
ExtremeMETA: High-speed Lightweight Image Segmentation Model by Remodeling Multi-channel Metamaterial Imagers
In this paper, we propose a large kernel lightweight segmentation model, ExtremeMETA.
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
Registration of point clouds collected from a pair of distant vehicles provides a comprehensive and accurate 3D view of the driving scenario, which is vital for driving safety related applications, yet existing literature suffers from the expensive pose label acquisition and the deficiency to generalize to new data distributions.
PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation
Understanding the anatomy of renal pathology is crucial for advancing disease diagnostics, treatment evaluation, and clinical research.
Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak."
$M^{2}$Fusion: Bayesian-based Multimodal Multi-level Fusion on Colorectal Cancer Microsatellite Instability Prediction
The contribution of the paper is three-fold: (1) $M^{2}$Fusion is the first pipeline of multi-level fusion on pathology WSI and 3D radiology CT image for MSI prediction; (2) CT images are the first time integrated into multimodal fusion for CRC MSI prediction; (3) feature-level fusion strategy is evaluated on both Transformer-based and CNN-based method.
Untying the Reversal Curse via Bidirectional Language Model Editing
A new evaluation metric of reversibility is introduced, and a benchmark dubbed as Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate the reversibility of edited models in recalling knowledge in the reverse direction of editing.
DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable Convolution
We hypothesize that deformable convolution can be an exploratory alternative to combine all advantages from the previous operators, providing long-range dependency, adaptive spatial aggregation and computational efficiency as a foundation backbone.
Evaluation Kidney Layer Segmentation on Whole Slide Imaging using Convolutional Neural Networks and Transformers
However, very few, if any, deep learning based approaches have been applied to kidney layer structure segmentation.
Spatial Pathomics Toolkit for Quantitative Analysis of Podocyte Nuclei with Histology and Spatial Transcriptomics Data in Renal Pathology
Podocytes, specialized epithelial cells that envelop the glomerular capillaries, play a pivotal role in maintaining renal health.
Integrating Offline Reinforcement Learning with Transformers for Sequential Recommendation
To this end, we train a farsighted recommender by using an offline RL algorithm with the policy network in our model architecture that has been initialized from a pre-trained transformer model.
Digital Modeling on Large Kernel Metamaterial Neural Network
However, the digital design of the metamaterial neural network (MNN) is fundamentally limited by its physical limitations, such as precision, noise, and bandwidth during fabrication.
Density-invariant Features for Distant Point Cloud Registration
Registration of distant outdoor LiDAR point clouds is crucial to extending the 3D vision of collaborative autonomous vehicles, and yet is challenging due to small overlapping area and a huge disparity between observed point densities.
Ranked #1 on
Point Cloud Registration
on nuScenes (Distant PCR)
All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning
The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach.
Intelligent Multi-channel Meta-imagers for Accelerating Machine Vision
Rapid developments in machine vision have led to advances in a variety of industries, from medical image analysis to autonomous systems.
Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning
The contribution of this paper is threefold: (1) We proposed a molecular-empowered learning scheme for multi-class cell segmentation using partial labels from lay annotators; (2) The proposed method integrated Giga-pixel level molecular-morphology cross-modality registration, molecular-informed annotation, and molecular-oriented segmentation model, so as to achieve significantly superior performance via 3 lay annotators as compared with 2 experienced pathologists; (3) A deep corrective learning (learning with imperfect label) method is proposed to further improve the segmentation performance using partially annotated noisy data.
MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead.
SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction
The proposed encoder is capable of interactively capturing complementary information between features and contextual information, to derive language-agnostic representations for various IE tasks.
GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding
Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention.
APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstruction
Such features are then used for online distant point cloud registration.
Ranked #3 on
Point Cloud Registration
on nuScenes (Distant PCR)
USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER
A method named Statistical Construction and Dual Adaptation of Gazetteer (SCDAG) is proposed for Multilingual Complex NER.
Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging
However, it does not consistently achieve satisfying performance for dense instance object segmentation, even with 20 prompts (clicks/boxes) on each image.
MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
Mobile monocular 3D object detection (Mono3D) (e. g., on a vehicle, a drone, or a robot) is an important yet challenging task.
MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation
To this end, we utilize a pose detection network to estimate the pose of the camera and then construct a feature map portraying pixel-level ground depth according to the 3D-to-2D perspective geometry.
Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation
We hypothesize that convolution with LK sizes is limited to maintain an optimal convergence for locality learning.
Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels.
WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition
In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently.
Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised Learning
In order to extract and separate compound figures into usable individual images for downstream learning, we propose a simple compound figure separation (SimCFS) framework without using the traditionally required detection bounding box annotations, with a new loss function and a hard case simulation.
Omni-Seg: A Scale-aware Dynamic Network for Renal Pathological Image Segmentation
The contribution of this paper is three-fold: (1) a novel scale-aware controller is proposed to generalize the dynamic neural network from single-scale to multi-scale; (2) semi-supervised consistency regularization of pseudo-labels is introduced to model the inter-scale correlation of unannotated tissue types into a single end-to-end learning paradigm; and (3) superior scale-aware generalization is evidenced by directly applying a model trained on human kidney images to mouse kidney images, without retraining.
Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization
Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies.
Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT
Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity Recognition (NER), as well as on cross-lingual model transfer.
Survival Prediction of Brain Cancer with Incomplete Radiology, Pathology, Genomics, and Demographic Data
Thus, there are still open questions on how to effectively predict brain cancer survival from the incomplete radiological, pathological, genomic, and demographic data (e. g., one or more modalities might not be collected for a patient).
USTC-NELSLIP at SemEval-2022 Task 11: Gazetteer-Adapted Integration Network for Multilingual Complex Named Entity Recognition
The proposed method is applied to several state-of-the-art Transformer-based NER models with a gazetteer built from Wikidata, and shows great generalization ability across them.
Multi-Level Contrastive Learning for Cross-Lingual Alignment
Cross-language pre-trained models such as multilingual BERT (mBERT) have achieved significant performance in various cross-lingual downstream NLP tasks.
Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling
Advertisers play an essential role in many e-commerce platforms like Taobao and Amazon.
Omni-Seg: A Single Dynamic Network for Multi-label Renal Pathology Image Segmentation using Partially Labeled Data
Computer-assisted quantitative analysis on Giga-pixel pathology images has provided a new avenue in histology examination.
Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South Central Andes
Recently, systematic manual survey of satellite and aerial imagery has enabled continuous distributional views of archaeological phenomena at interregional scales.
Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching
When speaking of sponsored search, bid keyword recommendation is the fundamental service.
Detecting Speaker Personas from Conversational Texts
This is a many-to-many semantic matching task because both contexts and personas in SPD are composed of multiple sentences.
Compound Figure Separation of Biomedical Images with Side Loss
Our technical contribution is three-fold: (1) we introduce a new side loss that is designed for compound figure separation; (2) we introduce an intra-class image augmentation method to simulate hard cases; (3) the proposed framework enables an efficient deployment to new classes of images, without requiring resource extensive bounding box annotations.
VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning
Recently, pixel embedding-based cell instance segmentation and tracking provided a neat and generalizable computing paradigm for understanding cellular dynamics.
SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning
Given a passage and the corresponding question, a participating system is expected to choose the correct answer from five candidates of abstract concepts in a cloze-style machine reading comprehension setup.
Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots
Empirical studies on the Persona-Chat dataset show that the partner personas neglected in previous studies can improve the accuracy of response selection in the IMN- and BERT-based models.
SimTriplet: Simple Triplet Representation Learning with a Single GPU
The contribution of the paper is three-fold: (1) The proposed SimTriplet method takes advantage of the multi-view nature of medical images beyond self-augmentation; (2) The method maximizes both intra-sample and inter-sample similarities via triplets from positive pairs, without using negative samples; and (3) The recent mix precision training is employed to advance the training by only using a single GPU with 16GB memory.
Tree frog-inspired nanopillar arrays for enhancement of adhesion and friction
Bioinspired structure adhesives have received increasing interest for many applications, such as climbing robots and medical devices.
Soft Condensed Matter
ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations
Contribution: The contribution of this paper is three-fold: (1) the proposed method aggregates adversarial simulations and single-stage pixel-embedding based deep learning; (2) the method is assessed with both the cellular (i. e., HeLa cells) and subcellular (i. e., microvilli) objects; and (3) to the best of our knowledge, this is the first study to explore annotation-free instance segmentation and tracking study for microscope videos.
Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
Task-oriented conversational modeling with unstructured knowledge access, as track 1 of the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to generate response given dialogue history and knowledge access.
Exploring End-to-End Differentiable Natural Logic Modeling
We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components.
CaCL: Class-aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns
Our contribution is three-fold: (1) we approach the weakly supervised segmentation from a novel codebook learning perspective; (2) the CaCL algorithm segments diffuse image patterns rather than focal objects; and (3) the proposed algorithm is implemented in a multi-task framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) via joint image reconstruction, classification, feature embedding, and segmentation.
ASIST: Annotation-free synthetic instance segmentation and tracking for microscope video analysis
Instance object segmentation and tracking provide comprehensive quantification of objects across microscope videos.
GAN based Unsupervised Segmentation: Should We Match the Exact Number of Objects
To match the number of objects at the micro-level, the novel fluorescence-based micro-level matching approach was presented.
Program Enhanced Fact Verification with Verbalization and Graph Attention Network
Built on that, we construct the graph attention verification networks, which are designed to fuse different sources of evidences from verbalized program execution, program structures, and the original statements and tables, to make the final verification decision.
Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking
With both embedding simulation and empirical validation via the four cohorts from the ISBI cell tracking challenge, the proposed Faster Mean-shift algorithm achieved 7-10 times speedup compared to the state-of-the-art embedding based cell instance segmentation and tracking algorithm.
Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots
The challenges of building knowledge-grounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously.
DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to.
Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots.
Ranked #2 on
Conversational Response Selection
on Ubuntu IRC
Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems
The NOESIS II challenge, as the Track 2 of the 8th Dialogue System Technology Challenges (DSTC 8), is the extension of DSTC 7.
Ranked #1 on
Conversation Disentanglement
on irc-disentanglement
Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking
We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8).
Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
The distances between context and response utterances are employed as a prior component when calculating the attention weights.
Ranked #10 on
Conversational Response Selection
on E-commerce
Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots
Compared with previous persona fusion approaches which enhance the representation of a context by calculating its similarity with a given persona, the DIM model adopts a dual matching architecture, which performs interactive matching between responses and contexts and between responses and personas respectively for ranking response candidates.
Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
Natural language inference (NLI) is among the most challenging tasks in natural language understanding.
Condition-Transforming Variational AutoEncoder for Conversation Response Generation
This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs).
Exploring Unsupervised Pretraining and Sentence Structure Modelling for Winograd Schema Challenge
Winograd Schema Challenge (WSC) was proposed as an AI-hard problem in testing computers' intelligence on common sense representation and reasoning.
Promoting Diversity for End-to-End Conversation Response Generation
At this stage, two different models are proposed, i. e., a variational generative (VariGen) model and a retrieval based (Retrieval) model.
Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
In this paper, we propose an interactive matching network (IMN) for the multi-turn response selection task.
Ranked #9 on
Conversational Response Selection
on E-commerce
The USTC-NEL Speech Translation system at IWSLT 2018
This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018.
Building Sequential Inference Models for End-to-End Response Selection
This paper presents an end-to-end response selection model for Track 1 of the 7th Dialogue System Technology Challenges (DSTC7).
Ranked #5 on
Conversational Response Selection
on DSTC7 Ubuntu
Word Embeddings based on Fixed-Size Ordinally Forgetting Encoding
In this paper, we propose to learn word embeddings based on the recent fixed-size ordinally forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence into a fixed-size representation.
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge
The PDP task we investigate in this paper is a complex coreference resolution task which requires the utilization of commonsense knowledge.
Ranked #63 on
Coreference Resolution
on Winograd Schema Challenge
Part-of-Speech Relevance Weights for Learning Word Embeddings
The model proposed in this paper paper jointly optimizes word vectors and the POS relevance matrices.
Probabilistic Reasoning via Deep Learning: Neural Association Models
We propose to use neural networks to model association between any two events in a domain.
Ranked #11 on
Natural Language Understanding
on PDP60
Integrate Document Ranking Information into Confidence Measure Calculation for Spoken Term Detection
The confidence measure of each term occurrence is then re-estimated through linear interpolation with the calculated document ranking weight to improve its reliability by integrating document-level information.
