Search Results for author:
Found 195 papers, 91 papers with code
The NiuTrans System for the WMT20 Quality Estimation Shared Task
This paper describes the submissions of the NiuTrans Team to the WMT 2020 Quality Estimation Shared Task.
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.
A Semantic Filter Based on Relations for Knowledge Graph Completion
experiments on the benchmark datasets show that the semantic filter based on relations can suppress the impact of other attribute dimensions and improve link prediction performance.
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering
Hyperspectral image (HSI) clustering assigns similar pixels to the same class without any annotations, which is an important yet challenging task.
SoK: Machine Unlearning for Large Language Models
Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch.
Phenotypic Profile-Informed Generation of Drug-Like Molecules via Dual-Channel Variational Autoencoders
The de novo generation of drug-like molecules capable of inducing desirable phenotypic changes is receiving increasing attention.
Efficient Long CoT Reasoning in Small Language Models
Experimental results across a series of mathematical reasoning benchmarks demonstrate the effectiveness of the proposed method in distilling long CoT reasoning ability into SLMs which maintains the competitive performance but significantly reduces generating redundant reasoning steps.
EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association
We propose a novel framework that enables the scalable generation of product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
Multimodal Retrieval-Augmented Generation (MRAG) systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities.
MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
To overcome these limitations, we introduce MORALISE, a comprehensive benchmark for evaluating the moral alignment of vision-language models (VLMs) using diverse, expert-verified real-world data.
Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
Recent advances in long-context models (LCMs), designed to handle extremely long input contexts, primarily focus on utilizing external contextual information, often leaving the influence of large language models' intrinsic knowledge underexplored.
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing ``pseudo reasoning paths'' imitated from expert models.
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates
Foundation medical segmentation models, with MedSAM being the most popular, have achieved promising performance across organs and lesions.
A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models
With the advancement of web techniques, they have significantly revolutionized various aspects of people's lives.
ViLBench: A Suite for Vision-Language Process Reward Modeling
Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajectories for complex tasks.
Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts.
Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation
We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images.
Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce
Additionally, we introduce EaP_lite, which entirely replaces the natural language components of prompts with labeled examples.
GMG: A Video Prediction Method Based on Global Focus and Motion Guided
Recent years, weather forecasting has gained significant attention.
Ranked #11 on
Video Prediction
on Moving MNIST
Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agents
With the advancement of conversational large language models (LLMs), several LLM-based Conversational Shopping Agents (CSA) have been developed to help customers smooth their online shopping.
A Practical Memory Injection Attack against LLM Agents
During the injection of the malicious record, we propose an indication prompt to guide the agent to autonomously generate our designed bridging steps.
SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures
The key insight of GBC lies in its effectiveness in modeling the morphological information of cracks, while the SASS enhances the perception of crack topology and texture by strengthening the continuity of semantic information between crack pixels.
Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
In light of this, we explore the feasibility of representation fine-tuning, which applied some linear update to a few representations in a learned subspace, for knowledge editing.
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation
Large Language Models (LLMs) can enhance their capabilities as AI assistants by integrating external tools, allowing them to access a wider range of information.
How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities
Drawing inspiration from recent discussions on search and learning, we systematically explore the complementary relationship between search and Large Language Models (LLMs) from three perspectives.
A General Framework to Enhance Fine-tuning-based LLM Unlearning
Unlearning has been proposed to remove copyrighted and privacy-sensitive data from Large Language Models (LLMs).
Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
Specifically, context-robust LLMs should rely on external context only when lacking internal knowledge, identify contradictions between internal and external knowledge, and disregard unhelpful contexts.
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
Chain-of-Thought (CoT) reasoning, which breaks down complex tasks into intermediate reasoning steps, has significantly enhanced the performance of large language models (LLMs) on challenging tasks.
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
For structured data, such as knowledge graphs, GraphRAG has been widely used to retrieve relevant information.
Demand Analysis under Price Rigidity and Endogenous Assortment: An Application to China's Tobacco Industry
We observe nominal price rigidity in tobacco markets across China.
Baichuan-Omni-1.5 Technical Report
We introduce Baichuan-Omni-1. 5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities.
Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?
However, these evaluations typically use a balanced dataset, where the number of inconsistent and consistent names are equal.
Computational Protein Science in the Era of Large Language Models (LLMs)
As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems.
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
This challenge is particularly pronounced in tasks involving multi-step processes, such as logical reasoning and multi-hop question answering, where understanding implicit relationships between entities and leveraging multi-hop connections in the given context are crucial.
Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models
To address these gaps, we propose to benchmark the concept removal methods by introducing a new dataset, Six-CD, along with a novel evaluation metric.
Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression
During inference, our framework further employs a variance minimization strategy across image augmentations that simulate common quality issues in echocardiogram acquisition, along with differential adaptation rates for periodic and aperiodic components.
Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses
Given a pair of perturbed expression profiles, our approach decouples the perturbation representations from basal states through domain separation encoders and then cross-transfers them in the latent space.
Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions
The rise of large language models (LLMs) offers new opportunities for automatic error detection in education, particularly for math word problems (MWPs).
Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models
As large language models (LLMs) become increasingly embedded in civic, educational, and political information environments, concerns about their potential political bias have grown.
A Survey of Calibration Process for Black-Box LLMs
Black-Box LLMs, despite their superior performance, pose heightened requirements for calibration techniques due to their API-only interaction constraints.
Dynamic Prompt Allocation and Tuning for Continual Test-Time Adaptation
For known domains, the corresponding domain-specific prompt is directly selected, while for previously unseen domains, a new prompt is allocated.
Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning
In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels.
Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data modalities.
Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data
However, the large size and high computation demands of LLMs limit their practicality in many applications, especially when further fine-tuning is required.
HC$^3$L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesis
Methods and materials: We propose a novel hybrid conditional latent diffusion model for efficient and accurate CBCT-to-CT synthesis, named HC$^3$L-Diff.
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.
Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation
Spectral variations pose a common challenge in analyzing hyperspectral images (HSI).
SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains
Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge.
Catastrophic Failure of LLM Unlearning via Quantization
Machine unlearning has been introduced as a viable solution to remove the influence of such problematic content without the need for costly and time-consuming retraining.
Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations
Large language models (LLMs) are employed to simulate human-like responses in social surveys, yet it remains unclear if they develop biases like social desirability response (SDR) bias.
Divide-Verify-Refine: Aligning LLM Responses with Complex Instructions
An alternative is to leverage LLMs' self-correction capabilities, allowing them to adjust responses to better meet specified constraints.
Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study
To better understand how ICL integrates the examples with the knowledge learned by the LLM during pre-training (i. e., pre-training knowledge) and how the examples impact ICL, this paper conducts a theoretical study in binary classification tasks.
Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e. g., low-quality images or a Gaussian distribution.
A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization
Open-ended short-answer questions (SAGs) have been widely recognized as a powerful tool for providing deeper insights into learners' responses in the context of learning analytics (LA).
TCDformer-based Momentum Transfer Model for Long-term Sports Prediction
Then it decomposes the reconstructed time series with momentum transfer into trend and seasonal components.
The Application of Machine Learning in Tidal Evolution Simulation of Star-Planet Systems
We also extracted features of planetary migration states and utilized lightGBM to classify the samples into 6 categories for prediction.
Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation
The F1 and mIoU scores on the TUT dataset are 0. 8382 and 0. 8473, respectively, achieving state-of-the-art (SOTA) performance while requiring the least computational resources.
Exploring Query Understanding for Amazon Product Search
Next, we delve into how the query understanding system contributes to understanding the performance of a ranking model.
A Survey of Mamba
In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel.
tcrLM: a lightweight protein language model for predicting T cell receptor and epitope binding specificity
These findings demonstrate the potential of tcrLM in predicting TCR-antigen binding specificity, with significant implications for advancing immunotherapy and personalized medicine.
Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
To address these gaps, we propose to benchmark the concept removal methods by introducing a new dataset, Six-CD, along with a novel evaluation metric.
A Pure Transformer Pretraining Framework on Text-attributed Graphs
Pretraining plays a pivotal role in acquiring generalized knowledge from large-scale data, achieving remarkable successes as evidenced by large models in CV and NLP.
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents.
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
First, the absence of a comprehensive benchmark with unified problem settings hinders a clear understanding of the comparative effectiveness and practical value of different text-space GFMs.
Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning
Large Language Models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities from few-shot demonstration exemplars.
Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs and a high-pass filter for heterophilic graphs.
UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models
Concurrently, to augment overall accuracy in question answering, we further adapt the Retrieval-Augmented Generation (RAG) process to the knowledge graph.
NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \textit{without} the need for training.
Dose-aware Diffusion Model for 3D PET Image Denoising: Multi-institutional Validation with Reader Study and Real Low-dose Data
However, existing models have often resulted in compromised image quality when achieving low-count/low-dose PET and have limited generalizability to different image noise-levels, acquisition protocols, and patient populations.
Modeling Selective Feature Attention for Representation-based Siamese Text Matching
Representation-based Siamese networks have risen to popularity in lightweight text matching due to their low deployment and inference costs.
Graph Machine Learning in the Era of Large Language Models (LLMs)
Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.
Explanation based Bias Decoupling Regularization for Natural Language Inference
The robustness of Transformer-based Natural Language Inference encoders is frequently compromised as they tend to rely more on dataset biases than on the intended task-relevant features.
RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering
We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images.
A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules
In this paper, we propose UnifyImmun, a unified cross-attention transformer model designed to simultaneously predict the bindings of peptides to both receptors, providing more comprehensive evaluation of antigen immunogenicity.
Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)
Teachers' mathematical content knowledge (CK) is of vital importance and need in teacher professional development (PD) programs.
SIFiD: Reassess Summary Factual Inconsistency Detection with LLM
Ensuring factual consistency between the summary and the original document is paramount in summarization tasks.
Towards generalization of drug response prediction to single cells and patients utilizing importance-aware multi-source domain transfer learning
The advancement of single-cell sequencing technology has promoted the generation of a large amount of single-cell transcriptional profiles, providing unprecedented opportunities to identify drug-resistant cell subpopulations within a tumor.
Towards Calibrated Deep Clustering Network
Specifically, we propose a novel dual-head (calibration head and clustering head) deep clustering model that can effectively calibrate the estimated confidence and the actual accuracy.
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI 3-D structure, and their optimization targets are not clustering-oriented.
Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing
JPEG compression can significantly impair the performance of adversarial face examples, which previous adversarial attacks on face recognition (FR) have not adequately addressed.
Rethinking Large Language Model Architectures for Sequential Recommendations
This design stems from our empirical observation that beam search decoding is ultimately unnecessary for sequential recommendations.
Mixture of Link Predictors on Graphs
Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning.
TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection
The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia.
Copyright Protection in Generative AI: A Technical Perspective
We examine from two distinct viewpoints: the copyrights pertaining to the source data held by the data owners and those of the generative models maintained by the model builders.
Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
Spatio-temporal forecasting is crucial in various fields and requires a careful balance between identifying subtle patterns and filtering out noise.
Ranked #5 on
Traffic Prediction
on BJTaxi
Robust Domain Misinformation Detection via Multi-modal Feature Alignment
We also propose a framework that simultaneously considers application scenarios of domain generalization (in which the target domain data is unavailable) and domain adaptation (in which unlabeled target domain data is available).
Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning
Phenotype-based screening has attracted much attention for identifying cell-active compounds.
Vision meets mmWave Radar: 3D Object Perception Benchmark for Autonomous Driving
This kind of radar format can enable machine learning models to generate more reliable object perception results after interacting and fusing the information or features between the camera and radar.
Cross-domain feature disentanglement for interpretable modeling of tumor microenvironment impact on drug response
This paper proposed a domain adaptation network for feature disentanglement to separate representations of cancer cells and TME of a tumor in patients.
Global Structure-Aware Diffusion Process for Low-Light Image Enhancement
To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory.
Ranked #4 on
Low-Light Image Enhancement
on LOL
Spectral-Aware Augmentation for Enhanced Graph Representation Learning
In this paper, we present GASSER, a model that applies tailored perturbations to specific frequencies of graph structures in the spectral domain, guided by spectral hints.
Efficient and Effective Deep Multi-view Subspace Clustering
i) The parameter scale of the FC layer is quadratic to sample numbers, resulting in high time and memory costs that significantly degrade their feasibility in large-scale datasets.
Label-free Node Classification on Graphs with Large Language Models (LLMS)
In light of these observations, this work introduces a label-free node classification on graphs with LLMs pipeline, LLM-GNN.
FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
FT-Shield addresses copyright protection challenges by designing new watermark generation and detection strategies.
On the Generalization of Training-based ChatGPT Detection Methods
ChatGPT is one of the most popular language models which achieve amazing performance on various natural language tasks.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
Federated Learning in Big Model Era: Domain-Specific Multimodal Large Models
Preliminary experiments show that enterprises can enhance and accumulate intelligent capabilities through multimodal model federated learning, thereby jointly creating an smart city model that provides high-quality intelligent services covering energy infrastructure safety, residential community security, and urban operation management.
Improving Text Semantic Similarity Modeling through a 3D Siamese Network
Siamese networks have gained popularity as a method for modeling text semantic similarity.
TVPR: Text-to-Video Person Retrieval and a New Benchmark
To the best of our knowledge, MFGF is the first successful attempt to use video for text-based person retrieval task and has achieved state-of-the-art performance on TVPReid dataset.
Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs
The most popular pipeline for learning on graphs with textual node attributes primarily relies on Graph Neural Networks (GNNs), and utilizes shallow text embedding as initial node representations, which has limitations in general knowledge and profound semantic understanding.
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective
In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning.
Ranked #5 on
Text-based de novo Molecule Generation
on ChEBI-20
Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models
Results from the experiments demonstrate that there is a significant performance gap between the in-distribution (ID) and OOD settings for document images, and that fine-grained analysis of distribution shifts can reveal the brittle nature of existing pre-trained VDU models and OOD generalization algorithms.
DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
By detecting the watermark from generated images, copyright infringement can be exposed with evidence.
Self-Explainable Graph Neural Networks for Link Prediction
Directly adopting existing post-hoc explainers for explaining link prediction is sub-optimal because: (i) post-hoc explainers usually adopt another strategy or model to explain a target model, which could misinterpret the target model; and (ii) GNN explainers for node classification identify crucial subgraphs around each node for the explanation; while for link prediction, one needs to explain the prediction for each pair of nodes based on graph structure and node attributes.
Interpretable Multimodal Misinformation Detection with Logic Reasoning
Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information.
T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering
To address these issues, we propose a novel method termed T-SciQ that aims at teaching science question answering with LLM signals.
TCR: Short Video Title Generation and Cover Selection with Attention Refinement
In this paper, we first collect and present a real-world dataset named Short Video Title Generation (SVTG) that contains videos with appealing titles and covers.
Counterfactual Learning on Graphs: A Survey
To facilitate the development of this promising direction, in this survey, we categorize and comprehensively review papers on graph counterfactual learning.
GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation
Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i. e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative.
ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction
To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples.
Models See Hallucinations: Evaluating the Factuality in Video Captioning
In this work, we conduct a detailed human evaluation of the factuality in video captioning and collect two annotated factuality datasets.
Single-Cell Multimodal Prediction via Transformers
The recent development of multimodal single-cell technology has made the possibility of acquiring multiple omics data from individual cells, thereby enabling a deeper understanding of cellular states and dynamics.
Single Cells Are Spatial Tokens: Transformers for Spatial Transcriptomic Data Imputation
In particular, investigate the following two key questions: (1) $\textit{how to encode spatial information of cells in transformers}$, and (2) $\textit{ how to train a transformer for transcriptomic imputation}$.
Generative Diffusion Models on Graphs: Methods and Applications
Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years.
Generating Concise Patches for Newly Released Programming Assignments
The key to such approaches is to fix a faulty program by making it equivalent to one of its correct reference programs whose overall structure is identical to that of the faulty submission.
Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models
In this paper, we propose a new model architecture with alignment-enriched tuning (dubbed AETNet) upon pre-trained document image models, to adapt downstream tasks with the joint task-specific supervised and alignment-aware contrastive objective.
EGRC-Net: Embedding-induced Graph Refinement Clustering Network
To begin, we leverage both semantic and topological information by employing a vanilla auto-encoder and a graph convolution network, respectively, to learn a latent feature representation.
Personalized Federated Learning for Multi-task Fault Diagnosis of Rotating Machinery
Intelligent fault diagnosis is essential to safe operation of machinery.
Contrastive Learning enhanced Author-Style Headline Generation
In this paper, we propose a novel Seq2Seq model called CLH3G (Contrastive Learning enhanced Historical Headlines based Headline Generation) which can use the historical headlines of the articles that the author wrote in the past to improve the headline generation of current articles.
Adaptive Fuzzy Tracking Control with Global Prescribed-Time Prescribed Performance for Uncertain Strict-Feedback Nonlinear Systems
Adaptive fuzzy control strategies are established to achieve global prescribed performance with prescribed-time convergence for strict-feedback systems with mismatched uncertainties and unknown nonlinearities.
Probabilistic Categorical Adversarial Attack & Adversarial Training
To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discrete optimization problem to a continuous problem that can be solved efficiently by Projected Gradient Descent.
Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples
In this paper, we propose an AutoEncoder-based Adversarial Examples (AEAE) detector, that can guard DNN models by detecting adversarial examples with low computation in an unsupervised manner.
Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement
In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attention mechanism and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm.
Learning A Locally Unified 3D Point Cloud for View Synthesis
To tackle this challenging problem, we propose a new deep learning-based view synthesis paradigm that learns a locally unified 3D point cloud from source views.
Task-Balanced Distillation for Object Detection
To alleviate this problem, a novel Task-decoupled Feature Distillation (TFD) is proposed by flexibly balancing the contributions of classification and regression tasks.
Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising
This paper tackles the challenging problem of hyperspectral (HS) image denoising.
Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation
In this letter, we propose a novel semi-supervised subspace clustering method, which is able to simultaneously augment the initial supervisory information and construct a discriminative affinity matrix.
Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity
The limitation can be attributed to the binding specificity of T cell receptor (TCR) to peptide-MHC complex (pMHC).
Attention-wise masked graph contrastive learning for predicting molecular property
We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph mask, to generate challenging positive sample for contrastive learning.
Contrastive learning-based computational histopathology predict differential expression of cancer driver genes
We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological feature in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes.
A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society.
Learning Fair Models without Sensitive Attributes: A Generative Approach
The lack of sensitive attributes challenges many existing fair classifiers.
Syntax-Aware Network for Handwritten Mathematical Expression Recognition
In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network.
Content-aware Warping for View Synthesis
To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network.
Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection
Experimental results show that the contribution of image transformations to adversarial detection is significantly different, the combination of them can significantly improve the generic detection ability against state-of-the-art adversarial attacks.
Interpretable Low-Resource Legal Decision Making
In this work, we utilize deep learning models in the area of trademark law to shed light on the issue of likelihood of confusion between trademarks.
Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels
To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes.
Deep Attention-guided Graph Clustering with Dual Self-supervision
Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance limitation.
Learning to Detect Open Carry and Concealed Object with 77GHz Radar
Detecting harmful carried objects plays a key role in intelligent surveillance systems and has widespread applications, for example, in airport security.
Toward Annotator Group Bias in Crowdsourcing
We conduct experiments on both synthetic and real-world datasets.
Interpretable Multi-hop Reasoning for Forecasting Future Links on Temporal Knowledge Graphs
The interpretability of the current temporal KG forecasting models is manifested in providing the reasoning paths.
Adaptive Attribute and Structure Subspace Clustering Network
In this paper, we propose a novel adaptive attribute and structure subspace clustering network (AASSC-Net) to simultaneously consider the attribute and structure information in an adaptive graph fusion manner.
Unsupervised Conversation Disentanglement through Co-Training
For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier.
Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines
In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation.
Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild
Specifically, on the basis of the intrinsic imaging degradation model of RGB images from HS images, we progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective unsupervised camera spectral response function estimation.
Graph2MDA: a multi-modal variational graph embedding model for predicting microbe-drug associations
We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods.
Attention-driven Graph Clustering Network
The combination of the traditional convolutional network (i. e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph convolutional network captures the topological graph feature.
Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images
Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient.
Enhancing Descriptive Image Captioning with Natural Language Inference
In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions.
Video Paragraph Captioning as a Text Summarization Task
Most previous methods simplify this task by using ground-truth event segments.
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features
In this paper, we reveal that imperceptible adversarial examples are the product of recessive features misleading neural networks, and an adversarial attack is essentially a kind of method to enrich these recessive features in the image.
AutoLoss: Automated Loss Function Search in Recommendations
Unlike existing algorithms, the proposed controller can adaptively generate the loss probabilities for different data examples according to their varied convergence behaviors.
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.
Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment
Radar has long been a common sensor on autonomous vehicles for obstacle ranging and speed estimation.
Hidden Backdoors in Human-Centric Language Models
We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.
Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning
In this paper, we explore to improve pretrained models with label hierarchies on the ZS-MTC task.
Self-supervised Symmetric Nonnegative Matrix Factorization
Inspired by ensemble clustering that aims to seek a better clustering result from a set of clustering results, we propose self-supervised SNMF (S$^3$NMF), which is capable of boosting clustering performance progressively by taking advantage of the sensitivity to initialization characteristic of SNMF, without relying on any additional information.
Thermal properties of light mesons from holography
The thermal widths increase rapidly above the chiral crossover temperature $T_{cp}$, indicating the dissociations of mesons at high temperature.
High Energy Physics - Phenomenology High Energy Physics - Theory
Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses
Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy.
RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization
Finally, we propose a method to evaluate the object detection performance of the RODNet.
Contact three-manifolds with exactly two simple Reeb orbits
It is known that every contact form on a closed three-manifold has at least two simple Reeb orbits, and a generic contact form has infinitely many.
Symplectic Geometry Dynamical Systems
Learning Light-Weight Translation Models from Deep Transformer
We proposed a novel group-permutation based knowledge distillation approach to compressing the deep Transformer model into a shallow model.
Clustering Ensemble Meets Low-rank Tensor Approximation
The existing clustering ensemble methods generally construct a co-association matrix, which indicates the pairwise similarity between samples, as the weighted linear combination of the connective matrices from different base clusterings, and the resulting co-association matrix is then adopted as the input of an off-the-shelf clustering algorithm, e. g., spectral clustering.
Maximum Entropy Subspace Clustering Network
Furthermore, we design a novel framework to explicitly decouple the auto-encoder module and the self-expressiveness module.
RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition
Millimeter-wave radars are being increasingly integrated into commercial vehicles to support new advanced driver-assistance systems by enabling robust and high-performance object detection, localization, as well as recognition - a key component of new environmental perception.
GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial Attack
Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs).
Shallow-to-Deep Training for Neural Machine Translation
We find that stacking layers is helpful in improving the representation ability of NMT models and adjacent layers perform similarly.
Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning
Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality.
Yet Meta Learning Can Adapt Fast, It Can Also Break Easily
Thus, in this paper, we perform the initial study about adversarial attacks on meta learning under the few-shot classification problem.
Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection
To address these challenges, in this paper, we propose OC4Seq, a multi-scale one-class recurrent neural network for detecting anomalies in discrete event sequences.
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
This report summarizes the results of the first edition of the challenge together with the findings of the participants.
Jointly Learning to Align and Summarize for Neural Cross-Lingual Summarization
However, it is a big challenge for the model to directly learn cross-lingual summarization as it requires learning to understand different languages and learning how to summarize at the same time.
Memory-efficient Embedding for Recommendations
Specifically, we first proposed an end-to-end differentiable framework that can calculate the weights over various dimensions for feature fields in a soft and continuous manner with an AutoML based optimization algorithm; then we derive a hard and discrete embedding component architecture according to the maximal weights and retrain the whole recommender framework.
Sequence to Point Learning Based on Bidirectional Dilated Residual Network for Non Intrusive Load Monitoring
Non Intrusive Load Monitoring (NILM) or Energy Disaggregation (ED), seeks to save energy by decomposing corresponding appliances power reading from an aggregate power reading of the whole house.
Attacking Black-box Recommendations via Copying Cross-domain User Profiles
In this work, we present our framework CopyAttack, which is a reinforcement learning based black-box attack method that harnesses real users from a source domain by copying their profiles into the target domain with the goal of promoting a subset of items.
Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation
On the basis of the novel tensor low-rank norm, we formulate MVSC as a convex low-rank tensor recovery problem, which is then efficiently solved with an augmented Lagrange multiplier based method iteratively.
TSFEL: Time Series Feature Extraction Library
Time series feature extraction is one of the preliminary steps of conventional machine learning pipelines.
RODNet: Radar Object Detection Using Cross-Modal Supervision
Radar is usually more robust than the camera in severe driving scenarios, e. g., weak/strong lighting and bad weather.
Experiments with mmWave Automotive Radar Test-bed
Millimeter-wave (mmW) radars are being increasingly integrated in commercial vehicles to support new Adaptive Driver Assisted Systems (ADAS) for its ability to provide high accuracy location, velocity, and angle estimates of objects, largely independent of environmental conditions.
Learning Multi-level Dependencies for Robust Word Recognition
Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises.
Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving
Specifically, we design, implement and evaluate a channel-based update algorithm for the central server in a distributed system, which selects the channels with regard to the most active features in a training loop and uploads them as learned information from local datasets.
Does Gender Matter? Towards Fairness in Dialogue Systems
In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models.
Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning
Artificial neural network has achieved unprecedented success in a wide variety of domains such as classifying, predicting and recognizing objects.
Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i. e., images, graphs and text.
DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems
However, most RL-based advertising algorithms focus on optimizing ads' revenue while ignoring the possible negative influence of ads on user experience of recommended items (products, articles and videos).
The NiuTrans Machine Translation Systems for WMT19
We participated in 13 translation directions, including 11 supervised tasks, namely EN↔{ZH, DE, RU, KK, LT}, GU→EN and the unsupervised DE↔CS sub-track.
INS: An Interactive Chinese News Synthesis System
So it is of vital importance to automatically synthesize a batch of news articles related to the event or topic into a new synthesis article (or overview article) for reader's convenience.
Clustering-aware Graph Construction: A Joint Learning Perspective
Graph-based clustering methods have demonstrated the effectiveness in various applications.
Whole-Chain Recommendations
With the recent prevalence of Reinforcement Learning (RL), there have been tremendous interests in developing RL-based recommender systems.
Multi-agent Reinforcement Learning
Recommendation Systems
+2
Towards Explainable NLP: A Generative Explanation Framework for Text Classification
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions.
Three-Dimensional Radiotherapy Dose Prediction on Head and Neck Cancer Patients with a Hierarchically Densely Connected U-net Deep Learning Architecture
The treatment planning process for patients with head and neck (H&N) cancer is regarded as one of the most complicated due to large target volume, multiple prescription dose levels, and many radiation-sensitive critical structures near the target.
