Search Results for author:
Found 60 papers, 29 papers with code
EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction
Multi-triple extraction is a challenging task due to the existence of informative inter-triple correlations, and consequently rich interactions across the constituent entities and relations. While existing works only explore entity representations, we propose to explicitly introduce relation representation, jointly represent it with entities, and novelly align them to identify valid triples. We perform comprehensive experiments on document-level relation extraction and joint entity and relation extraction along with ablations to demonstrate the advantage of the proposed method.
Document-level Relation Extraction
Joint Entity and Relation Extraction
+2
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
However, a comprehensive benchmark for systematically evaluating the capabilities of these agents remains absent.
Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing
In this study, we argue that ideal consistent 3D editing can be achieved through a \textit{progressive-views paradigm}, which propagates editing semantics from the editing-salient view to other editing-sparse views.
Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
The results lead to several key findings that add new insights upon existing understandings: 1) Rationales can, at times, deteriorate model performance; 2) Rationales can, at times, improve model reliability, even outperforming their untrained counterparts; 3) A linear correspondence exists in between the performance and reliability improvements, while both are driven by the intrinsic difficulty of the task.
MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning
Complex tasks involving tool integration pose significant challenges for Large Language Models (LLMs), leading to the emergence of multi-agent workflows as a promising solution.
Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking
We synthesize self-reflected trajectories that include reflections and corrections of error steps, which enhance the effectiveness of LLM agents in learning from teacher models, enabling them to become agents capable of self-reflecting and correcting.
Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
To address this limitation, we propose a novel \textit{Residual Alignment Model} (\textit{RAM}) that formalizes the alignment process as a type of importance sampling.
CL-RAG: Bridging the Gap in Retrieval-Augmented Generation with Curriculum Learning
Inspired by human cognitive learning, curriculum learning trains models using samples progressing from easy to difficult, thus enhancing their generalization ability, and we integrate this effective paradigm to the training of the RAG system.
HDGlyph: A Hierarchical Disentangled Glyph-Based Framework for Long-Tail Text Rendering in Diffusion Models
Visual text rendering, which aims to accurately integrate specified textual content within generated images, is critical for various applications such as commercial design.
DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization
To address this, we introduce DualReal, a novel framework that, employs adaptive joint training to collaboratively construct interdependencies between dimensions.
HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression
While large language models (LLMs) have proven effective in leveraging textual data for recommendations, their application to multimodal recommendation tasks remains relatively underexplored.
Leveraging Robust Optimization for LLM Alignment under Distribution Shifts
Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values.
RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
RealGeneral demonstrates effectiveness in multiple important visual generation tasks, e. g., it achieves a 14. 5% improvement in subject similarity for customized generation and a 10% enhancement in image quality for canny-to-image task.
On-the-fly Preference Alignment via Principle-Guided Decoding
These limitations significantly constrain the scope and efficacy of both task-specific and general preference alignment methods.
Dragin3D: Image Editing by Dragging in 3D Space
This modification helps improve the model's ability to ignore background interference when editing real images with complex backgrounds.
FeedEdit: Text-Based Image Editing with Dynamic Feedback Regulation
Previous works mainly follow the multi-step denoising diffusion paradigm, which adopts a fixed text guidance intensity (i. e., editing intensity) to inject textual features, while ignoring the step-specific editing requirements.
A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models
During Coupling Space Projection, all attention features of the pretrained adapter are aggregated to fully capture the coupling relationship before being projected into a unified space.
SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
Vision-language temporal alignment is a crucial capability for human dynamic recognition and cognition in real-world scenarios.
D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation
To address these limitations, we propose dynamically compressing different image regions by recognizing the importance of different regions, and introduce a novel two-stage framework designed to enhance the effectiveness and efficiency of image generation: (1) Dynamic VAE (DVAE) at first stage employs a hierarchical encoder to encode different image regions at different downsampling rates, tailored to their specific information densities, thereby providing more accurate and natural latent codes for the diffusion process.
Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection
In each layer of GNN, node features aggregate information from their neighboring nodes to update their information.
FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values.
CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization
This misconstruction leads to both overfitting or underfitting of irrelevant and intrinsic attributes of the subject, i. e., these attributes are over-represented or under-represented simultaneously, causing a trade-off between similarity and controllability.
RealCustom++: Representing Images as Real-Word for Real-Time Customization
Text-to-image customization, which takes given texts and images depicting given subjects as inputs, aims to synthesize new images that align with both text semantics and subject appearance.
ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
To overcome this challenge, we propose ELDER, a novel approach to create a continuous association between data and adapters.
Dual-path Collaborative Generation Network for Emotional Video Captioning
Emotional Video Captioning is an emerging task that aims to describe factual content with the intrinsic emotions expressed in videos.
LIRE: listwise reward enhancement for preference alignment
Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content.
Feature-Adaptive and Data-Scalable In-Context Learning
In this paper, we propose a feature-adaptive and data-scalable in-context learning framework (FADS-ICL), which can leverage task-adaptive features to promote inference on the downstream task, with the supervision of beyond-context samples.
Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
Furthermore, a batch attention module is also proposed in this paper to alleviate the problem of missing sentimental samples, caused by the data imbalance, which is common in live videos as the popularity of videos varies.
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods.
RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
However, the inherent entangled influence scope of pseudo-words with the given text results in a dual-optimum paradox, i. e., the similarity of the given subjects and the controllability of the given text could not be optimal simultaneously.
Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing
GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes.
Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions.
Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment
We propose a novel Linguistic-Aware Patch Slimming (LAPS) framework for fine-grained alignment which explicitly identifies redundant visual patches with language supervision and rectifies their semantic and spatial information to facilitate more effective and consistent patch-word alignment.
E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation
Then we propose an emotion correlation enhanced decoder, with a novel correlation-aware aggregation and soft/hard strategy, respectively improving the emotion perception and response generation.
Grammatical Error Correction via Mixed-Grained Weighted Training
In this paper, the inherent discrepancies are manifested in two aspects, namely, accuracy of data annotation and diversity of potential annotations.
On the Calibration of Large Language Models and Alignment
As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time.
Improving Image Captioning via Predicting Structured Concepts
Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly.
Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation
We analyze this phenomenon and reveal that entity codes, the quantization outcomes for expressing entities, have higher entropy at the code level and Jaccard distance at the codeword level under random entity quantization.
Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation
Then we design a novel attribute distribution reconstruction method to balance the obtained distributions and use the reconstructed distributions to guide language models for generation, effectively avoiding the issue of Attribute Collapse.
DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation
While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centric images, an intractable problem is how to preserve the face identity for conditioned face images.
ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
The answering quality of an aligned large language model (LLM) can be drastically improved if treated with proper crafting of prompts.
Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation
Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook.
Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook.
Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers
Relation prediction on knowledge graphs (KGs) is a key research topic.
$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
In-Context Learning (ICL), which formulates target tasks as prompt completion conditioned on in-context demonstrations, has become the prevailing utilization of LLMs.
Learning Semantic Relationship Among Instances for Image-Text Matching
Image-text matching, a bridge connecting image and language, is an important task, which generally learns a holistic cross-modal embedding to achieve a high-quality semantic alignment between the two modalities.
Crossing the Gap: Domain Generalization for Image Captioning
In this paper, we introduce a new setting called Domain Generalization for Image Captioning (DGIC), where the data from the target domain is unseen in the learning process.
Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning
They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations.
ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting
In this paper, we argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input.
Ranked #4 on
Text Spotting
on SCUT-CTW1500
UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations.
Ranked #1 on
Relation Extraction
on WebNLG
Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity
In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction (CPP) to improve CSC, and, for the first time, systematically discuss the adaptivity and granularity of this auxiliary task.
DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation
Text-to-image generation aims at generating realistic images which are semantically consistent with the given text.
Negative-Aware Attention Framework for Image-Text Matching
Image-text matching, as a fundamental task, bridges the gap between vision and language.
Lesion-Aware Transformers for Diabetic Retinopathy Grading
First, to the best of our knowledge, this is the first work to formulate lesion discovery as a weakly supervised lesion localization problem via a transformer decoder.
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively.
Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction
Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN.
Ranked #3 on
Relation Extraction
on DocRED
Overcoming Language Priors with Self-supervised Learning for Visual Question Answering
Our method can compensate for the data biases by generating balanced data without introducing external annotations.
Image Captioning with Context-Aware Auxiliary Guidance
Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image.
Curriculum Learning for Natural Language Understanding
With the great success of pre-trained language models, the pretrain-finetune paradigm now becomes the undoubtedly dominant solution for natural language understanding (NLU) tasks.
Graph Structured Network for Image-Text Matching
The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase.
Ranked #18 on
Cross-Modal Retrieval
on Flickr30k
