Search Results for author:
Found 44 papers, 16 papers with code
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks
Specifically, we re-formulate both token and sentence classification tasks into a unified language modeling task, and map label spaces of different tasks into the same vocabulary space.
An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism
Entity alignment (EA) aims to discover the equivalent entity pairs between KGs, which is a crucial step for integrating multi-source KGs. For a long time, most researchers have regarded EA as a pure graph representation learning task and focused on improving graph encoders while paying little attention to the decoding process. In this paper, we propose an effective and efficient EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI). Specifically, we derive two sets of isomorphism equations: (1) Adjacency tensor isomorphism equations and (2) Gramian tensor isomorphism equations. By combining these equations, DATTI could effectively utilize the adjacency and inner correlation isomorphisms of KGs to enhance the decoding process of EA. Extensive experiments on public datasets indicate that our decoding algorithm can deliver significant performance improvements even on the most advanced EA methods, while the extra required time is less than 3 seconds.
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack
To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones.
TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks.
VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
In this paper, we exploit the inherent temporal non-uniformity of real-world videos and observe that videos exhibit dynamic information density, with high-motion segments demanding greater detail preservation than static scenes.
A Weighted Predict-and-Optimize Framework for Power System Operation Considering Varying Impacts of Uncertainty
Integrating prediction and optimization enhances decision-making quality by yielding near optimal solutions.
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space.
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution
Image diffusion models have been adapted for real-world video super-resolution to tackle over-smoothing issues in GAN-based methods.
Online Low-Carbon Workload, Energy, and Temperature Management of Distributed Data Centers
Data centers have become one of the major energy consumers, making their low-carbon operations critical to achieving global carbon neutrality.
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
Our approach not only enhances computational efficiency but also aligns naturally with image generation principles by operating in continuous token space and following a hierarchical generation process from coarse to fine details.
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
Text-to-video generation has evolved rapidly in recent years, delivering remarkable results.
Learnable Infinite Taylor Gaussian for Dynamic View Rendering
Capturing the temporal evolution of Gaussian properties such as position, rotation, and scale is a challenging task due to the vast number of time-varying parameters and the limited photometric data available, which generally results in convergence issues, making it difficult to find an optimal solution.
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models.
Frontiers of Deep Learning: From Novel Application to Real-World Deployment
Deep learning continues to re-shape numerous fields, from natural language processing and imaging to data analytics and recommendation systems.
SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization
Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent variations.
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens.
Enhancing In-Context Learning via Implicit Demonstration Augmentation
The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters.
CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
A naive method is to simply increase the masking ratio and the likelihood of masking attack tokens, but it leads to a significant reduction in both certified accuracy and the certified radius due to input corruption by extensive masking.
Boosting Model Resilience via Implicit Adversarial Data Augmentation
This insight leads us to develop a meta-learning-based framework for optimizing classifiers with this novel loss, introducing the effects of augmentation while bypassing the explicit augmentation process.
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs.
CodeShell Technical Report
Through this process, We have curated 100 billion high-quality pre-training data from GitHub.
Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent
A deep Q-network, pre-trained with the original features and their corresponding pseudo labels, is employed to improve the efficacy of the exploration process in feature selection.
Generative Retrieval with Large Language Models
When completing knowledge-intensive tasks, humans sometimes need not just an answer but also a corresponding reference passage for auxiliary reading.
Addressing Distribution Shift in Time Series Forecasting with Instance Normalization Flows
Due to non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting.
Exploiting Duality in Open Information Extraction with Predicate Prompt
Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence.
A Multi-timescale and Chance-Constrained Energy Dispatching Strategy of Integrated Heat-Power Community with Shared Hybrid Energy Storage
In the integrated heat-power system with coupling heat-power generators and demands, the key challenges lie in the interaction between heat and power, the inherent uncertainty of renewable energy and consumers' demands, and the multi-timescale scheduling of heat and power.
Towards Visual Taxonomy Expansion
Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8. 75 %.
AOG-LSTM: An adaptive attention neural network for visual storytelling
Moreover, the existing method of alleviating error accumulation based on replacing reference words does not take into account the different effects of each word.
Ranked #20 on
Visual Storytelling
on VIST
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
To ensure the reliability of PandaLM, we collect a diverse human-annotated test dataset, where all contexts are generated by humans and labels are aligned with human preferences.
Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction
The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks.
Exploiting Pseudo Image Captions for Multimodal Summarization
Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives.
Causality-aware Concept Extraction based on Knowledge-guided Prompting
The prompt adopts the topic of the given entity from the existing knowledge in KGs to mitigate the spurious co-occurrence correlations between entities and biased concepts.
Exploring Vision-Language Models for Imbalanced Learning
However, their performance on imbalanced dataset is relatively poor, where the distribution of classes in the training dataset is skewed, leading to poor performance in predicting minority classes.
Optimal Sampling Designs for Multi-dimensional Streaming Time Series with Application to Power Grid Sensor Data
When applied to European power grid consumption data, the proposed leverage score based sampling methods outperform the benchmark sampling method in online estimation and prediction.
Sizing Grid-Connected Wind Power Generation and Energy Storage with Wake Effect and Endogenous Uncertainty: A Distributionally Robust Method
In this paper, a bi-objective distributionally robust optimization (DRO) model is proposed to determine the capacities of wind power generation and ESSs considering the wake effect.
A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking
We noted that the distinctness of the domain-specific features is different, so in this paper, we propose to use a curriculum learning strategy based on keyword weight ranking to improve the performance of multi-domain text classification models.
Focus Is What You Need For Chinese Grammatical Error Correction
Chinese Grammatical Error Correction (CGEC) aims to automatically detect and correct grammatical errors contained in Chinese text.
Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension
In order to supply existing KGs with more fine-grained and new concepts, we propose a novel concept extraction framework, namely MRC-CE, to extract large-scale multi-granular concepts from the descriptive texts of entities.
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.
Can Pre-trained Language Models Interpret Similes as Smart as Human?
In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i. e., to let the PLMs infer the shared properties of similes.
Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach
Code summaries are brief natural language descriptions of source code pieces.
Graph Enhanced Dual Attention Network for Document-Level Relation Extraction
Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relational facts.
Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning
Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance.
Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data
In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class.
