Search Results for author:
Found 82 papers, 39 papers with code
XInfoTabS: Evaluating Multilingual Tabular Natural Language Inference
In this paper, we use machine translation methods to construct a multilingual tabular NLI dataset, namely XINFOTABS, which expands the English tabular NLI dataset of INFOTABS to ten diverse languages.
Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning
On the downstream tabular inference task, using only the automatically extracted evidence as the premise, our approach outperforms prior benchmarks.
Representation Learning of Tangled Key-Value Sequence Data for Early Classification
To address this problem, we propose a novel method, i. e., Key-Value sequence Early Co-classification (KVEC), which leverages both inner- and inter-correlations of items in a tangled key-value sequence through key correlation and value correlation to learn a better sequence representation.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
Latent CLAP Loss for Better Foley Sound Synthesis
We introduce a new loss term to enhance Foley sound generation in AudioLDM without post-filtering.
TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks.
InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
We further explore how to use LEAN to solve math problems and study its performance under the setting of multi-task learning which shows the possibility of using LEAN as a unified platform for solving and proving in math.
Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence
Then we compute and update the protein-ligand interaction embedding based on the protein residue-level embeddings and ligand atom-level embeddings, and the geometric constraints in the inferred protein contact map and ligand distance map.
CoLLiE: Collaborative Training of Large Language Models in an Efficient Way
This paper introduces CoLLiE, an efficient library that facilitates collaborative training of large language models using 3D parallelism, parameter-efficient fine-tuning (PEFT) methods, and optimizers such as Lion, Adan, Sophia, LOMO and AdaLomo.
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes.
Ranked #1 on
Drug Discovery
on QM9
TempTabQA: Temporal Question Answering for Semi-Structured Tables
Given these results, our dataset has the potential to serve as a challenging benchmark to improve the temporal reasoning capabilities of NLP models.
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models
Additionally, experiments on 18 datasets further demonstrate that Monkey surpasses existing LMMs in many tasks like Image Captioning and various Visual Question Answering formats.
Scaling Laws of RoPE-based Extrapolation
The extrapolation capability of Large Language Models (LLMs) based on Rotary Position Embedding is currently a topic of considerable interest.
RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem.
Enhancing Adversarial Attacks: The Similar Target Method
Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns.
ControlRetriever: Harnessing the Power of Instructions for Controllable Retrieval
Recent studies have shown that dense retrieval models, lacking dedicated training data, struggle to perform well across diverse retrieval tasks, as different retrieval tasks often entail distinct search intents.
AFN: Adaptive Fusion Normalization via an Encoder-Decoder Framework
The success of deep learning is inseparable from normalization layers.
Learning Universal and Robust 3D Molecular Representations with Graph Convolutional Networks
To combine the DNP descriptor and chemical features in molecules, we construct the Robust Molecular Graph Convolutional Network (RoM-GCN) which is capable to take both node and edge features into consideration when generating molecule representations.
InfoSync: Information Synchronization across Multilingual Semi-structured Tables
The proposed method includes 1) Information Alignment to map rows and 2) Information Update for updating missing/outdated information for aligned tables across multilingual tables.
Towards Explainable Conversational Recommender Systems
To achieve this, we conduct manual and automatic approaches to extend these dialogues and construct a new CRS dataset, namely Explainable Recommendation Dialogues (E-ReDial).
Healing Unsafe Dialogue Responses with Weak Supervision Signals
Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus.
MERGE: Fast Private Text Generation
The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-based models.
The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models
Large language models often necessitate grounding on external knowledge to generate faithful and reliable answers.
V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception
To facilitate the development of cooperative perception, we present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception.
HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones
In this paper, we propose addressing these challenges using HiSSNet (Hierarchical SED and SID Network).
View Adaptive Light Field Deblurring Networks with Depth Perception
On the other hand, because the blur degree also varies with the depth of the object, a depth perception view attention is designed to deblur different depth areas by selectively integrating information from different views.
Multi-Action Dialog Policy Learning from Logged User Feedback
To cope with this problem, we explore to improve multi-action dialog policy learning with explicit and implicit turn-level user feedback received for historical predictions (i. e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios.
MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation
We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further.
Multi-Head Feature Pyramid Networks for Breast Mass Detection
Analysis of X-ray images is one of the main tools to diagnose breast cancer.
Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction
We find in practice simply adding the subtask might confuse the main task learning, hence Multi-task Attention Module is proposed to deal with the feature interaction between the multiple learning targets.
UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems
We present an extensible user simulation toolkit to facilitate automatic evaluation of conversational recommender systems.
Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network.
Ring That Bell: A Corpus and Method for Multimodal Metaphor Detection in Videos
We present the first openly available multimodal metaphor annotated corpus.
Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction
In this work, we propose a Graph Neural Network (GNN)-based scoring function trained only with the atomic types and coordinates on limited solved RNA 3D structures for distinguishing accurate structural models.
Realistic Data Augmentation Framework for Enhancing Tabular Reasoning
We observed that our framework could generate human-like tabular inference examples, which could benefit training data augmentation, especially in the scenario with limited supervision.
Enhancing Tabular Reasoning with Pattern Exploiting Training
Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e. g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across inputs while reasoning over the tabular data.
Active Learning on a Programmable Photonic Quantum Processor
Here, we design and implement two AL-enpowered variational quantum classifiers, to investigate the potential applications and effectiveness of AL in quantum machine learning.
Parameter-Parallel Distributed Variational Quantum Algorithm
Variational quantum algorithms (VQAs) have emerged as a promising near-term technique to explore practical quantum advantage on noisy intermediate-scale quantum (NISQ) devices.
PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training
Unlike most existing semi-supervised learning methods, adversarial training based methods distinguish samples from different sources by learning the data distribution of the segmentation map, leading the segmenter to generate more accurate predictions.
Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes
On small molecule dataset for predicting quantum chemical properties, PaxNet reduces the prediction error by 15% and uses 73% less memory than the best baseline.
Molecular Property Prediction
Protein-Ligand Affinity Prediction
Light Field Raindrop Removal via 4D Re-sampling
In this paper, we propose a novel LFRR network by directly utilizing the complementary pixel information of raindrop-free areas in the input raindrop LF, which consists of the re-sampling module and the refinement module.
Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
User simulation has been a cost-effective technique for evaluating conversational recommender systems.
"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses.
Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems
Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities.
StruBERT: Structure-aware BERT for Table Search and Matching
In this paper, we propose StruBERT, a structure-aware BERT model that fuses the textual and structural information of a data table to produce context-aware representations for both textual and tabular content of a data table.
DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction
We strictly prove that any permutation-invariant function implemented by DuMLP-Pin can be decomposed into two or more permutation-equivariant ones in a dot-product way as the cardinality of the given input set is greater than a threshold.
Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology
Advances in biomedicine are largely fueled by exploring uncharted territories of human biology.
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions.
Ranked #1 on
Question Answering
on TAT-QA
Semantic Table Retrieval using Keyword and Table Queries
The main novel contribution of this work is a semantic table retrieval framework for matching information needs (keyword or table queries) against tables.
Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems
The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like.
Domain-Specific Suppression for Adaptive Object Detection
The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one.
WTR: A Test Collection for Web Table Retrieval
We describe the development, characteristics and availability of a test collection for the task of Web table retrieval, which uses a large-scale Web Table Corpora extracted from the Common Crawl.
A simple low-degree optimal finite element scheme for the elastic transmission eigenvalue problem
The paper presents a finite element scheme for the elastic transmission eigenvalue problem written as a fourth order eigenvalue problem.
Numerical Analysis Numerical Analysis 31A30, 65N30, 47B07
Learning to Check Contract Inconsistencies
This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract.
Multi-RIS Aided 3D Secure Precise Wireless Transmission
Then, multiple RISs are utilized to achieve SPWT through the reflection path among transmitter, RISs and receivers in order to enhance the communication performance and energy efficiency simultaneously.
Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
The prediction of physicochemical properties from molecular structures is a crucial task for artificial intelligence aided molecular design.
Ranked #2 on
Drug Discovery
on QM9
PSF-LO: Parameterized Semantic Features Based Lidar Odometry
Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving.
IAI MovieBot: A Conversational Movie Recommender System
Conversational recommender systems support users in accomplishing recommendation-related goals via multi-turn conversations.
Multi-Dimension Fusion Network for Light Field Spatial Super-Resolution using Dynamic Filters
Light field cameras have been proved to be powerful tools for 3D reconstruction and virtual reality applications.
Generating Categories for Sets of Entities
Category systems are central components of knowledge bases, as they provide a hierarchical grouping of semantically related concepts and entities.
On the Secrecy of UAV Systems With Linear Trajectory
By observing the fact that moving in a straight line is a common flying behavior of unmanned aerial vehicles (UAVs) in normal applications, e. g., power line inspections, and air patrols along with highway/streets/borders, in this paper we investigate the secrecy outage performance of a UAV system with linear trajectory, where a UAV ($S$) flies in a straight line and transmits its information over the downlink to a legitimate receiver ($D$) on the ground while an eavesdropping UAV ($E$) trying to overhear the information delivery between $S$ and $D$.
Evaluating Conversational Recommender Systems via User Simulation
Conversational information access is an emerging research area.
3D Lidar Mapping Relative Accuracy Automatic Evaluation Algorithm
HD (High Definition) map based on 3D lidar plays a vital role in autonomous vehicle localization, planning, decision-making, perception, etc.
Accelerating Neural Network Inference by Overflow Aware Quantization
The inherent heavy computation of deep neural networks prevents their widespread applications.
Summarizing and Exploring Tabular Data in Conversational Search
We propose to generate natural language summaries as answers to describe the complex information contained in a table.
Novel Entity Discovery from Web Tables
We refer to this process as novel entity discovery and, to the best of our knowledge, it is the first endeavor on mining the unlinked cells in web tables.
Web Table Extraction, Retrieval and Augmentation: A Survey
Tables are a powerful and popular tool for organizing and manipulating data.
Auto-completion for Data Cells in Relational Tables
We address the task of auto-completing data cells in relational tables.
Quantum-enhanced least-square support vector machine: simplified quantum algorithm and sparse solutions
We also incorporate kernel methods into the above quantum algorithms, which uses both exponential growth Hilbert space of qubits and infinite dimensionality of continuous variable for quantum feature maps.
Recommending Related Tables
Tables are an extremely powerful visual and interactive tool for structuring and manipulating data, making spreadsheet programs one of the most popular computer applications.
Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation
To improve the performance of attention-based GNNs, we propose cardinality preserved attention (CPA) models that can be applied to any kind of attention mechanisms.
Ranked #2 on
Graph Classification
on RE-M5K
Data mining Mandarin tone contour shapes
In spontaneous speech, Mandarin tones that belong to the same tone category may exhibit many different contour shapes.
Residual Networks for Light Field Image Super-Resolution
Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously.
Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval
Tables contain valuable knowledge in a structured form.
Efforts estimation of doctors annotating medical image
In this paper, we propose a new criterion to evaluate efforts of doctors annotating medical image.
A Multi-channel Network with Image Retrieval for Accurate Brain Tissue Segmentation
Magnetic Resonance Imaging (MRI) is widely used in the pathological and functional studies of the brain, such as epilepsy, tumor diagnosis, etc.
DASN:Data-Aware Skilled Network for Accurate MR Brain Tissue Segmentation
It is on the basis of this, we propose a judgement to distinguish data sets that different models are good at.
Generating High-Quality Query Suggestion Candidates for Task-Based Search
We address the task of generating query suggestions for task-based search.
Ad Hoc Table Retrieval using Semantic Similarity
Specifically, we (i) represent queries and tables in multiple semantic spaces (both discrete sparse and continuous dense vector representations) and (ii) introduce various similarity measures for matching those semantic representations.
