Search Results for author:
Found 42 papers, 15 papers with code
Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns
We present a comprehensive study of sparse attention patterns in Transformer models.
Few-Shot Class-Incremental Learning for Named Entity Recognition
In this work, we study a more challenging but practical problem, i. e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones.
VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs
One understudied capability in VLMs is visual spatial planning -- the ability to comprehend the spatial arrangements of objects and devise action plans to achieve desired outcomes in visual scenes.
Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags
Despite recent advances in the general visual instruction-following ability of Multimodal Large Language Models (MLLMs), they still struggle with critical problems when required to provide a precise and detailed response to a visual instruction: (1) failure to identify novel objects or entities, (2) mention of non-existent objects, and (3) neglect of object's attributed details.
SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
Using raw images as the sole training data, our method achieves unprecedented performance in self-supervised open-world segmentation, marking a significant milestone towards high-quality open-world entity segmentation in the absence of human-annotated masks.
Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natural language input to produce an accurate visual output.
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion
Table question answering is a popular task that assesses a model's ability to understand and interact with structured data.
Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations
While these results are promising, follow-up works found that, within the multilingual embedding spaces, there exists strong language identity information which hinders the expression of linguistic factors shared across languages.
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning
In this paper, we focus on improving the prompt transfer from dialogue state tracking to dialogue summarization and propose Skeleton-Assisted Prompt Transfer (SAPT), which leverages skeleton generation as extra supervision that functions as a medium connecting the distinct source and target task and resulting in the model's better consumption of dialogue state information.
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
We then impose spatial attention control by combining the attention over the entire text description and that over the local description of the particular object in the corresponding pixel region of that object.
Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model
We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments.
Better Generative Replay for Continual Federated Learning
Federated learning is a technique that enables a centralized server to learn from distributed clients via communications without accessing the client local data.
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Based on this finding, we further propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation.
Hierarchical Conversational Preference Elicitation with Bandit Feedback
To achieve this, the recommender system conducts conversations with users, asking their preferences for different items or item categories.
Bundle MCR: Towards Conversational Bundle Recommendation
MCR, which uses a conversational paradigm to elicit user interests by asking user preferences on tags (e. g., categories or attributes) and handling user feedback across multiple rounds, is an emerging recommendation setting to acquire user feedback and narrow down the output space, but has not been explored in the context of bundle recommendation.
Unified Pretraining Framework for Document Understanding
Document intelligence automates the extraction of information from documents and supports many business applications.
Ranked #7 on
Document Layout Analysis
on PubLayNet val
EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval
recommendation, and marketing services.
Neural Point Process for Learning Spatiotemporal Event Dynamics
The key construction of our approach is the nonparametric space-time intensity function, governed by a latent process.
UniDoc: Unified Pretraining Framework for Document Understanding
Document intelligence automates the extraction of information from documents and supports many business applications.
Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation
For slow learning of graph similarity, this paper proposes a novel early-fusion approach by designing a co-attention-based feature fusion network on multilevel GNN features.
Automatic Forecasting via Meta-Learning
In this work, we develop techniques for fast automatic selection of the best forecasting model for a new unseen time-series dataset, without having to first train (or evaluate) all the models on the new time-series data to select the best one.
IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation
By employing score-based outlier detectors for initialization, iPOF updates each data point's outlier score by averaging the outlier factors of its nearest common neighbors.
SelfDoc: Self-Supervised Document Representation Learning
For downstream usage, we propose a novel modality-adaptive attention mechanism for multimodal feature fusion by adaptively emphasizing language and vision signals.
ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain.
RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Contrasted with prior work, this paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.
Edge: Enriching Knowledge Graph Embeddings with External Text
Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods.
Insight-centric Visualization Recommendation
This global ranking makes it difficult and time-consuming for users to find the most interesting or relevant insights.
Neural Point Process for Forecasting Spatiotemporal Events
To the best of our knowledge, this is the first neural point process model that can jointly predict both the space and time of events.
Adaptive Adversarial Network for Source-Free Domain Adaptation
Unsupervised Domain Adaptation solves knowledge transfer along with the coexistence of well-annotated source domain and unlabeled target instances.
Learning Contextualized Knowledge Graph Structures for Commonsense Reasoning
Recently, neural-symbolic architectures have achieved success on commonsense reasoning through effectively encoding relational structures retrieved from external knowledge graphs (KGs) and obtained state-of-the-art results in tasks such as (commonsense) question answering and natural language inference.
Neural Contextual Bandits with Deep Representation and Shallow Exploration
We study a general class of contextual bandits, where each context-action pair is associated with a raw feature vector, but the reward generating function is unknown.
Self-Supervised Relationship Probing
Structured representations of images that model visual relationships are beneficial for many vision and vision-language applications.
CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation
User profiles can capture prominent user behaviors from the history, and provide valuable signals about which kinds of path patterns are more likely to lead to potential items of interest for the user.
Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation.
Learning Contextualized Knowledge Structures for Commonsense Reasoning
Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks.
Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions
We propose a novel algorithm, named Open-Edit, which is the first attempt on open-domain image manipulation with open-vocabulary instructions.
Structured Policy Iteration for Linear Quadratic Regulator
In this paper, we introduce the \textit{Structured Policy Iteration} (S-PI) for LQR, a method capable of deriving a structured linear policy.
Learnable Subspace Clustering
This paper studies the large-scale subspace clustering (LSSC) problem with million data points.
Cross-Domain Document Object Detection: Benchmark Suite and Method
We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation.
Learning Robust Data Representation: A Knowledge Flow Perspective
It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch.
Scene Graph Generation with External Knowledge and Image Reconstruction
Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc.
Unpaired Image Captioning via Scene Graph Alignments
Most of current image captioning models heavily rely on paired image-caption datasets.
