Search Results for author:
Found 363 papers, 185 papers with code
Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
Multimodal named entity recognition and relation extraction (MNER and MRE) is a fundamental and crucial branch in information extraction.
Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation
In this paper, we propose to leverage word-formation knowledge to enhance Chinese WSD.
Dispersed EM-VAEs for Interpretable Text Generation
Interpretability is important in text generation for guiding the generation with interpretable attributes.
Improving Personalized Explanation Generation through Visualization
In modern recommender systems, there are usually comments or reviews from users that justify their ratings for different items.
Structural Supervision for Word Alignment and Machine Translation
Syntactic structure has long been argued to be potentially useful for enforcing accurate word alignment and improving generalization performance of machine translation.
CIST@CL-SciSumm 2020, LongSumm 2020: Automatic Scientific Document Summarization
In the LongSumm shared task, we integrate both the extractive and abstractive summarization ways.
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization
Based on the artificial dataset, we train an evaluation model that can not only make accurate and robust factual consistency discrimination but is also capable of making interpretable factual errors tracing by backpropagated gradient distribution on token embeddings.
Extractive Financial Narrative Summarisation based on DPPs
We participate in the FNS-Summarisation 2020 shared task to be held at FNP 2020 workshop at COLING 2020.
GLAT: Glancing at Latent Variables for Parallel Text Generation
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
Augmenting Legal Judgment Prediction with Contrastive Case Relations
Existing legal judgment prediction methods usually only consider one single case fact description as input, which may not fully utilize the information in the data such as case relations and frequency.
Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models
On text benchmarks, Core not only performs competitively to other frontier models on a set of well-established benchmarks (e. g. MMLU, GSM8K) but also outperforms GPT4-0613 on human evaluation.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario
Occlusions hinder point cloud frame alignment in LiDAR data, a challenge inadequately addressed by scene flow models tested mainly on occlusion-free datasets.
CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs
We have conducted extensive experiments to validate the performance of our proposed CHOPS architecture using the CPHOS-dataset, with the aim of demonstrating how LLMs can enhance or serve as alternatives to human customer service.
Unleashing the Potential of Large Language Models for Predictive Tabular Tasks in Data Science
Despite their proficiency in comprehending natural language, LLMs fall short in dealing with structured tabular data.
Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality
Video paragraph captioning (VPC) involves generating detailed narratives for long videos, utilizing supportive modalities such as speech and event boundaries.
To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of 3D Transfer Learning
Unfortunately, its applicability in 3D data processing has been relatively limited.
Convergence analysis of OT-Flow for sample generation
Second, since the loss function will be approximated by Monte Carlo method in training, we established the convergence between the discrete loss function and the continuous one when the sample number $N$ goes to infinity as well.
Deep Learning for Trajectory Data Management and Mining: A Survey and Beyond
In this paper, we present a comprehensive review of the development and recent advances in deep learning for trajectory computing (DL4Traj).
Entity6K: A Large Open-Domain Evaluation Dataset for Real-World Entity Recognition
Open-domain real-world entity recognition is essential yet challenging, involving identifying various entities in diverse environments.
Word Order's Impacts: Insights from Reordering and Generation Analysis
Existing works have studied the impacts of the order of words within natural text.
Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction
We present a novel, lightweight dual-attention ECG network designed to capture complex ECG features essential for early HF risk prediction, despite the notable imbalance between low and high-risk groups.
MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder
Within the domain of medical analysis, extensive research has explored the potential of mutual learning between Masked Autoencoders(MAEs) and multimodal data.
SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM
We have developed the \textbf{SnapNTell Dataset}, distinct from traditional VQA datasets: (1) It encompasses a wide range of categorized entities, each represented by images and explicitly named in the answers; (2) It features QA pairs that require extensive knowledge for accurate responses.
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
In this paper, we propose a novel jailbreaking attack against VLMs, aiming to bypass their safety barrier when a user inputs harmful instructions.
Tree Counting by Bridging 3D Point Clouds with Imagery
We leverage the fusion of three-dimensional LiDAR measurements and 2D imagery to facilitate the accurate counting of trees.
TempCompass: Do Video LLMs Really Understand Videos?
Motivated by these two problems, we propose the \textbf{TempCompass} benchmark, which introduces a diversity of temporal aspects and task formats.
Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models
To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension.
Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions
On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary.
Structure-Based Drug Design via 3D Molecular Generative Pre-training and Sampling
We develop a novel 3D graph editing model to generate molecules using fragments, and pre-train this model on abundant 3D ligands for learning target-independent properties.
Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages
Environmental conservation organizations routinely monitor news content on conservation in protected areas to maintain situational awareness of developments that can have an environmental impact.
Perils of Self-Feedback: Self-Bias Amplifies in Large Language Models
Recent studies show that self-feedback improves large language models (LLMs) on certain tasks while worsens other tasks.
DE-COP: Detecting Copyrighted Content in Language Models Training Data
We are motivated by the premise that a language model is likely to identify verbatim excerpts from its training text.
Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze
Improving factual consistency in abstractive summarization has been a focus of current research.
Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs
In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder.
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation
Mamba-UNet adopts a pure Visual Mamba (VMamba)-based encoder-decoder structure, infused with skip connections to preserve spatial information across different scales of the network.
Progress and Opportunities of Foundation Models in Bioinformatics
Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.
EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models
In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs).
KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models
We further theoretically prove that KS-Lottery can find the certified winning tickets in the embedding layer, fine-tuning on the found parameters is guaranteed to perform as well as full fine-tuning.
Weak-to-Strong Jailbreaking on Large Language Models
In this paper, we propose the weak-to-strong jailbreaking attack, an efficient method to attack aligned LLMs to produce harmful text.
Red Teaming Visual Language Models
Additionally, we simply apply red teaming alignment to LLaVA-v1. 5 with Supervised Fine-tuning (SFT) using RTVLM, and this bolsters the models' performance with 10% in RTVLM test set, 13% in MM-Hal, and without noticeable decline in MM-Bench, overpassing other LLaVA-based models with regular alignment data.
Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering
Central to our focus is the utilizing of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements.
Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential Recommendations
However, most existing retrieval models employ a single-round inference paradigm, which may not adequately capture the dynamic nature of user preferences and stuck in one area in the item space.
DarkShot: Lighting Dark Images with Low-Compute and High-Quality
This paper proposes a lightweight network that outperforms existing state-of-the-art (SOTA) methods in low-light enhancement tasks while minimizing computation.
SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label
This paper introduces SSFlowNet, a semi-supervised approach for scene flow estimation, that utilizes a blend of labeled and unlabeled data, optimizing the balance between the cost of labeling and the precision of model training.
Silkie: Preference Distillation for Large Visual Language Models
This paper explores preference distillation for large vision language models (LVLMs), improving their ability to generate helpful and faithful responses anchoring the visual context.
Ranked #17 on
Visual Question Answering
on MM-Vet
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solutions.
Ranked #13 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Seam-guided local alignment and stitching for large parallax images
However, the effectiveness of seam-cutting usually depends on that images can be roughly aligned such that there exists a local region where a plausible seam can be found.
GenZI: Zero-Shot 3D Human-Scene Interaction Generation
Given a natural language description and a coarse point location of the desired interaction in a 3D scene, we first leverage VLMs to imagine plausible 2D human interactions inpainted into multiple rendered views of the scene.
VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
The ability to perceive how objects change over time is a crucial ingredient in human intelligence.
UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning
In this paper, we propose UniHPE, a unified Human Pose Estimation pipeline, which aligns features from all three modalities, i. e., 2D human pose estimation, lifting-based and image-based 3D human pose estimation, in the same pipeline.
Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation
We further apply a guided diffusion model to domain adapt 3D adult pose to infant pose to supplement small datasets.
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
Recent large language models (LLM) are leveraging human feedback to improve their generation quality.
How Multilingual is Multilingual LLM?
Large Language Models (LLMs), trained predominantly on extensive English data, often exhibit limitations when applied to other languages.
Object-centric Cross-modal Feature Distillation for Event-based Object Detection
In this paper, we develop a novel knowledge distillation approach to shrink the performance gap between these two modalities.
FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation
The multi-aspect categorization of FETV enables fine-grained analysis of the metrics' reliability in different scenarios.
RPCANet: Deep Unfolding RPCA Based Infrared Small Target Detection
Deep learning (DL) networks have achieved remarkable performance in infrared small target detection (ISTD).
CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting
In light of this, we introduce the CPSeg, Chain-of-Thought Language Prompting for Finer-grained Semantic Segmentation), an innovative framework designed to augment image segmentation performance by integrating a novel "Chain-of-Thought" process that harnesses textual information associated with images.
Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding
Large language models (LLMs) have shown promising capabilities in using external tools to solve complex problems.
Functional Geometry Guided Protein Sequence and Backbone Structure Co-Design
In this paper, we propose NAEPro, a model to jointly design Protein sequence and structure based on automatically detected functional sites.
Learning Personalized Story Evaluation
We further develop a personalized story evaluation model PERSE to infer reviewer preferences and provide a personalized evaluation.
Joint Design of Protein Sequence and Structure based on Motifs
Designing novel proteins with desired functions is crucial in biology and chemistry.
Segment Any Building
The task of identifying and segmenting buildings within remote sensing imagery has perennially stood at the forefront of scholarly investigations.
Tool-Augmented Reward Modeling
We validate our approach across a wide range of domains, incorporating seven distinct external tools.
Edge Aware Learning for 3D Point Cloud
This paper proposes an innovative approach to Hierarchical Edge Aware 3D Point Cloud Learning (HEA-Net) that seeks to address the challenges of noise in point cloud data, and improve object recognition and segmentation by focusing on edge features.
Making Large Language Models Better Reasoners with Alignment
To address this problem, we introduce an \textit{Alignment Fine-Tuning (AFT)} paradigm, which involves three steps: 1) fine-tuning LLMs with COT training data; 2) generating multiple COT responses for each question, and categorizing them into positive and negative ones based on whether they achieve the correct answer; 3) calibrating the scores of positive and negative responses given by LLMs with a novel constraint alignment loss.
Large Language Models for Generative Recommendation: A Survey and Visionary Discussions
Large language models (LLM) not only have revolutionized the field of natural language processing (NLP) but also have the potential to reshape many other fields, e. g., recommender systems (RS).
Extrapolating Large Language Models to Non-English by Aligning Languages
We start from targeting individual languages by performing cross-lingual instruction-tuning (CoIT) on LLaMA, i. e. tuning it with translation task data and cross-lingual general task data to obtain cross-lingual models (x-LLaMAs), and formulate underlying scaling laws to investigate the advantages of using scalable translation data.
3D Shape-Based Myocardial Infarction Prediction Using Point Cloud Classification Networks
Myocardial infarction (MI) is one of the most prevalent cardiovascular diseases with associated clinical decision-making typically based on single-valued imaging biomarkers.
Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference
In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG) within a CDT platform.
Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation
Learning-based methods have dominated the 3D human pose estimation (HPE) tasks with significantly better performance in most benchmarks than traditional optimization-based methods.
Ranked #11 on
3D Human Pose Estimation
on 3DPW
(PA-MPJPE metric)
Provable Robust Watermarking for AI-Generated Text
We propose a robust and high-quality watermark method, Unigram-Watermark, by extending an existing approach with a simplified fixed grouping strategy.
DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences
In this paper, we introduces DIAS, a dataset specifically developed for IA segmentation in DSA sequences.
Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit
For the more challenging problem of pursuing multiple evading vehicles, these algorithms typically select a fixed target evading vehicle for pursuing vehicles without considering dynamic traffic situation, which significantly reduces pursuing success rate.
M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning
To tackle this challenge and promote research in the vision-language field, we introduce the Multi-Modal, Multilingual Instruction Tuning (M$^3$IT) dataset, designed to optimize VLM alignment with human instructions.
Invisible Image Watermarks Are Provably Removable Using Generative AI
However, if we do not require the watermarked image to look the same as the original one, watermarks that keep the image semantically similar can be an alternative defense against our attack.
Large Language Models are not Fair Evaluators
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e. g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models.
Neural Machine Translation with Dynamic Graph Convolutional Decoder
Existing wisdom demonstrates the significance of syntactic knowledge for the improvement of neural machine translation models.
ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories
Recently, Large Language Models (LLMs) have been serving as general-purpose interfaces, posing a significant demand for comprehensive visual knowledge.
ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers
To address these challenges, we propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness.
AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models
However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual rules in the environment.
INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback
By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report.
Learning from Mistakes via Cooperative Study Assistant for Large Language Models
In this paper, we propose Study Assistant for Large LAnguage Model (SALAM), a novel framework with an auxiliary agent to assist the main LLM in learning from mistakes through interactive cooperation.
Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks.
Can Language Models Understand Physical Concepts?
Language models~(LMs) gradually become general-purpose interfaces in the interactive and embodied world, where the understanding of physical concepts is an essential prerequisite.
Extrapolating Multilingual Understanding Models as Multilingual Generators
Considering that encoder-based models have the advantage of efficient generation and self-correction abilities, this paper explores methods to empower multilingual understanding models the generation abilities to get a unified model.
Can We Edit Factual Knowledge by In-Context Learning?
Inspired by in-context learning (ICL), a new paradigm based on demonstration contexts without parameter updating, we explore whether ICL can edit factual knowledge.
Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
However, as pre-trained language models (PLMs) continue to increase in size, the communication cost for transmitting parameters during synchronization has become a training speed bottleneck.
Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge.
HIORE: Leveraging High-order Interactions for Unified Entity Relation Extraction
Entity relation extraction consists of two sub-tasks: entity recognition and relation extraction.
Importance Weighted Expectation-Maximization for Protein Sequence Design
How can we efficiently generate diverse and novel protein sequences with high fitness?
Segment Anything Model for Medical Images?
To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks.
Revisiting k-NN for Fine-tuning Pre-trained Language Models
Pre-trained Language Models (PLMs), as parametric-based eager learners, have become the de-facto choice for current paradigms of Natural Language Processing (NLP).
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT).
Influence of Myocardial Infarction on QRS Properties: A Simulation Study
However, the influence of various MI properties on the QRS is not intuitively predictable. In this work, we have systematically investigated the effects of 17 post-MI scenarios, varying the location, size, transmural extent, and conductive level of scarring and border zone area, on the forward-calculated QRS.
Generalizable Local Feature Pre-training for Deformable Shape Analysis
We observe that with proper training, learned features can be useful in such tasks, but, crucially, only with an appropriate choice of the receptive field size.
ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models
In response to this lacuna, this paper introduces a pioneering contribution in the form of a text-to-waveform music generation model, underpinned by the utilization of diffusion models.
Aligning Multi-Sequence CMR Towards Fully Automated Myocardial Pathology Segmentation
For instance, balanced steady-state free precession cine sequences present clear anatomical boundaries, while late gadolinium enhancement and T2-weighted CMR sequences visualize myocardial scar and edema of MI, respectively.
Protecting Language Generation Models via Invisible Watermarking
We can then detect the secret message by probing a suspect model to tell if it is distilled from the protected one.
ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval
Diffusion models show promising generation capability for a variety of data.
Design and Implementation of A Soccer Ball Detection System with Multiple Cameras
This paper designed and implemented football detection system under multiple cameras for the detection and capture of targets in real-time matches.
One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER
Previous typical solutions mainly obtain a NER model by pre-trained language models (PLMs) with data from a rich-resource domain and adapt it to the target domain.
Geometric ergodicity of SGLD via reflection coupling
We consider the geometric ergodicity of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm under nonconvexity settings.
BuildSeg: A General Framework for the Segmentation of Buildings
Building segmentation from aerial images and 3D laser scanning (LiDAR) is a challenging task due to the diversity of backgrounds, building textures, and image quality.
Unsupervised Cardiac Segmentation Utilizing Synthesized Images from Anatomical Labels
In this work, we propose an unsupervised framework for multi-class segmentation with both intensity and shape constraints.
Multi-Target Landmark Detection with Incomplete Images via Reinforcement Learning and Shape Prior
This is particularly evident for the learning-based multi-target landmark detection, where algorithms could be misleading to learn primarily the variation of background due to the varying FOV, failing the detection of targets.
VQNet 2.0: A New Generation Machine Learning Framework that Unifies Classical and Quantum
Therefore, based on VQNet 1. 0, we further propose VQNet 2. 0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization.
A Survey on In-context Learning
With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few examples.
Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models
With increasing scale, large language models demonstrate both quantitative improvement and new qualitative capabilities, especially as zero-shot learners, like GPT-3.
Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation
To address the needs of learning representations for all languages in a unified space, we propose a novel efficient training recipe, upon which we build an effective detachable model, Lego-MT.
WACO: Word-Aligned Contrastive Learning for Speech Translation
In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation.
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
In this paper, we propose SESCORE2, a self-supervised approach for training a model-based metric for text generation evaluation.
LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing
In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural image CS.
Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GAN
Fine-grained semantic segmentation of a person's face and head, including facial parts and head components, has progressed a great deal in recent years.
Pre-trained Language Models Can be Fully Zero-Shot Learners
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data?
Accelerating Antimicrobial Peptide Discovery with Latent Structure
By sampling in the latent space, LSSAMP can simultaneously generate peptides with ideal sequence attributes and secondary structures.
Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
Given a possibly false claim sentence, how can we automatically correct it with minimal editing?
On Analyzing the Role of Image for Visual-enhanced Relation Extraction
Multimodal relation extraction is an essential task for knowledge graph construction.
MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences.
Gradient Knowledge Distillation for Pre-trained Language Models
Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student.
Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matching
Our approach is not only accurate with near-isometric input, for which a high spectral resolution is typically preferred, but also robust and able to produce reasonable matching even in the presence of significant non-isometric distortion, which poses great challenges to existing methods.
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models
We then design a Model Uncertainty--aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student.
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
Is it possible to build a general and automatic natural language generation (NLG) evaluation metric?
Calibrating Factual Knowledge in Pretrained Language Models
However, we find that facts stored in the PLMs are not always correct.
PARAGEN : A Parallel Generation Toolkit
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.
Distillation-Resistant Watermarking for Model Protection in NLP
We prove that a protected model still retains the original accuracy within a certain bound.
Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization
The issue of factual consistency in abstractive summarization has received extensive attention in recent years, and the evaluation of factual consistency between summary and document has become an important and urgent task.
Block-Structured Optimization for Subgraph Detection in Interdependent Networks
We propose a generalized framework for block-structured nonconvex optimization, which can be applied to structured subgraph detection in interdependent networks, such as multi-layer networks, temporal networks, networks of networks, and many others.
Safety-based Speed Control of a Wheelchair using Robust Adaptive Model Predictive Control
Electric-powered wheelchair plays an important role in providing accessibility for people with mobility impairment.
Multimodal Analogical Reasoning over Knowledge Graphs
Analogical reasoning is fundamental to human cognition and holds an important place in various fields.
SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence
In this work, we present a novel learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches, for robust non-rigid matching.
Rethinking the Unpretentious U-net for Medical Ultrasound Image Segmentation
However, variable tumor morphology, blurred boundary, and similar intensity distributions bring challenges for accurate segmentation of breast tumors.
3D Textured Shape Recovery with Learned Geometric Priors
3D textured shape recovery from partial scans is crucial for many real-world applications.
Multi-Modality Cardiac Image Computing: A Survey
Multi-modality cardiac imaging plays a key role in the management of patients with cardiovascular diseases.
A deep learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation
In this paper, we develop a deep learning framework to compute the geodesics under the spherical WFR metric, and the learned geodesics can be adopted to generate weighted samples.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
Deep Computational Model for the Inference of Ventricular Activation Properties
Cardiac digital twins can provide non-invasive characterizations of cardiac functions for individual patients, and therefore are promising for the patient-specific diagnosis and therapy stratification.
Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Prediction
Traditional knowledge distillation in classification problems transfers the knowledge via class correlations in the soft label produced by teacher models, which are not available in regression problems like stock trading volume prediction.
A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics
We establish a sharp uniform-in-time error estimate for the Stochastic Gradient Langevin Dynamics (SGLD), which is a popular sampling algorithm.
On uniform-in-time diffusion approximation for stochastic gradient descent
The main technique is to establish the exponential decay rates of the derivatives of the solution to the backward Kolmogorov equation.
On the Impact of Noises in Crowd-Sourced Data for Speech Translation
Training speech translation (ST) models requires large and high-quality datasets.
On the Learning of Non-Autoregressive Transformers
Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to reduce the decoding latency by predicting the whole sentences in parallel.
Decoupling Predictions in Distributed Learning for Multi-Center Left Atrial MRI Segmentation
In this work, we propose a new framework of distributed learning that bridges the gap between two groups, and improves the performance for both generic and local data.
Delving into the Openness of CLIP
However, evaluating the openness of CLIP-like models is challenging, as the models are open to arbitrary vocabulary in theory, but their accuracy varies in practice.
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.
Enhancing Cross-lingual Transfer by Manifold Mixup
Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances.
Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
To deal with these issues, we propose a novel Hierarchical Visual Prefix fusion NeTwork (HVPNeT) for visual-enhanced entity and relation extraction, aiming to achieve more effective and robust performance.
Cross-modal Contrastive Learning for Speech Translation
Learning similar representations for semantically similar speech and text is important for speech translation.
Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning
Note that the previous parametric learning paradigm can be viewed as memorization regarding training data as a book and inference as the close-book test.
Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
Since most MKGs are far from complete, extensive knowledge graph completion studies have been proposed focusing on the multimodal entity, relation extraction and link prediction.
Provably Confidential Language Modelling
Large language models are shown to memorize privacy information such as social security numbers in training data.
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
The success of Pre-Trained Models (PTMs) has reshaped the development of Natural Language Processing (NLP).
Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets
Can a robot autonomously learn to design and construct a bridge from varying-sized blocks without a blueprint?
Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching
The expansion of renewable energy could help realizing the goals of peaking carbon dioxide emissions and carbon neutralization.
Contextual Representation Learning beyond Masked Language Modeling
How do masked language models (MLMs) such as BERT learn contextual representations?
$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation
How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data?
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning
Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR).
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
How to learn highly compact yet effective sentence representation?
BEATS: An Open-Source, High-Precision, Multi-Channel EEG Acquisition Tool System
Commonly used EEG acquisition system's hardware and software are usually closed-source.
$ \text{T}^3 $OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area
Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games.
KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models
However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases (KBs), we need to further explore some critical features of PLMs.
Deepfake Network Architecture Attribution
With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images.
Personalized Prompt Learning for Explainable Recommendation
In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages.
Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion
For the label fusion, we design a similarity estimation network (SimNet), which estimates the fusion weight of each atlas by measuring its similarity to the target image.
AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images
Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods.
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images
Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on myocardium is the key to this assessment.
Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass
Quantification of forest biomass stocks and their dynamics is important for implementing effective climate change mitigation measures.
Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly reduce the retraining computational cost and the potential environmental side-effects.
Unsupervised Editing for Counterfactual Stories
We also propose a new metric to alleviate the shortcomings of current automatic metrics and better evaluate the trade-off.
StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks
Scene text detection is still a challenging task, as there may be extremely small or low-resolution strokes, and close or arbitrary-shaped texts.
Learning Logic Rules for Document-level Relation Extraction
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #21 on
Relation Extraction
on DocRED
A Survey on Green Deep Learning
In recent years, larger and deeper models are springing up and continuously pushing state-of-the-art (SOTA) results across various fields like natural language processing (NLP) and computer vision (CV).
Multi-Modality Cardiac Image Analysis with Deep Learning
Accurate cardiac computing, analysis and modeling from multi-modality images are important for the diagnosis and treatment of cardiac disease.
Self-Supervised Speech Denoising Using Only Noisy Audio Signals
The first module adopts a random audio sub-sampler on each noisy audio to generate training pairs.
CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level
In this paper, we present a large-scale Chinese news summarization dataset CNewSum, which consists of 304, 307 documents and human-written summaries for the news feed.
Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision
How do we perform efficient inference while retaining high translation quality?
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundary.
LightSeq2: Accelerated Training for Transformer-based Models on GPUs
In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs.
NAIL: A Challenging Benchmark for Na\"ive Logical Reasoning
Logical reasoning over natural text is an important capability towards human level intelligence.
Generating Antimicrobial Peptides from Latent Secondary Structure Space
By sampling in the latent secondary structure space, we can generate peptides with ideal amino acids and secondary structures at the same time.
Non-Autoregressive Models are Better Multilingual Translators
Multilingual machine translation aims to develop a single model for multiple language directions.
Knowledge Guided Geometric Editing for Unsupervised Drug Design
Deep learning models have been widely used in automatic drug design.
The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
Dynamic Knowledge Distillation for Pre-trained Language Models
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models.
Learning Kernel-Smoothed Machine Translation with Retrieved Examples
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining?
Learning When to Translate for Streaming Speech
Given a usually long speech sequence, we develop an efficient monotonic segmentation module inside an encoder-decoder model to accumulate acoustic information incrementally and detect proper speech unit boundaries for the input in speech translation task.
Multilingual Translation via Grafting Pre-trained Language Models
Can pre-trained BERT for one language and GPT for another be glued together to translate texts?
Right Ventricular Segmentation from Short- and Long-Axis MRIs via Information Transition
In this work, we propose an automatic RV segmentation framework, where the information from long-axis (LA) views is utilized to assist the segmentation of short-axis (SA) views via information transition.
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
Data augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations.
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting
Most NER methods rely on extensive labeled data for model training, which struggles in the low-resource scenarios with limited training data.
Secoco: Self-Correcting Encoding for Neural Machine Translation
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation
Separating 3D point clouds into individual instances is an important task for 3D vision.
MTG: A Benchmark Suite for Multilingual Text Generation
We introduce MTG, a new benchmark suite for training and evaluating multilingual text generation.
WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration
Instead of using a predefined fixed-size local support in voxelization, we propose to learn the optimal support in a data-driven manner.
Learning to Design and Construct Bridge without Blueprint
In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then manipulate the blocks reliably to construct a stable bridge according to the proposed design.
Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation
In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information.
Pre-training Methods for Neural Machine Translation
This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation.
