Search Results for author:
Found 112 papers, 49 papers with code
Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection
Despite the significant progress on this task, it is extremely time-consuming and budget-unfriendly to collect sufficient high-quality labeled data for every new target under fully-supervised learning, whereas unlabeled data can be collected easier.
TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation
The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation.
Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge
Furthermore, we utilize CSK to enrich edges with knowledge representations and process the SKAIG with a graph transformer.
Ranked #9 on
Emotion Recognition in Conversation
on DailyDialog
TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
Despite the commendable progress of recent LLM-based data synthesis methods, they face two limitations in generating table instruction tuning data.
Advantageous Parameter Expansion Training Makes Better Large Language Models
In this paper, we propose Advantageous Parameter EXpansion Training (APEX), a method that progressively expands advantageous parameters into the space of disadvantageous ones, thereby increasing their proportion and enhancing training effectiveness.
The Role of Video Generation in Enhancing Data-Limited Action Understanding
Based on this observation, the information enhancement strategy is proposed to enhance the informative content of the generated samples from two aspects: the environments and the characters.
Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning
Despite significant advancements in multimodal reasoning tasks, existing Large Vision-Language Models (LVLMs) are prone to producing visually ungrounded responses when interpreting associated images.
Multi-Modal Molecular Representation Learning via Structure Awareness
The multi-modal molecular representation learning module collaboratively processes information from different modalities of the same molecule to overcome intermodal differences and generate a unified molecular embedding.
Dynamic Early Exit in Reasoning Models
Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks.
NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
Processing structured tabular data, particularly lengthy tables, constitutes a fundamental yet challenging task for large language models (LLMs).
BeamLoRA: Beam-Constraint Low-Rank Adaptation
Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.
AS-GCL: Asymmetric Spectral Augmentation on Graph Contrastive Learning
To our knowledge, we are the first to encode augmentation views of the spectral domain using asymmetric encoders.
Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition
By utilizing low-rank and sparse parameters along with compression techniques, CEFGL significantly reduces communication complexity.
Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation
In addition, we propose a multi-round distillation paradigm to iteratively enrich the distillation datasets, thereby progressively improving the mathematical reasoning abilities of SLMs.
A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
The advent of large language models (LLMs) has significantly propelled the advancement of Role-Playing Agents (RPAs).
RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining
The remarkable development of text-to-image generation models has raised notable security concerns, such as the infringement of portrait rights and the generation of inappropriate content.
Orthogonal Finetuning for Direct Preference Optimization
Hence, we introduce orthogonal finetuning for DPO via a weight-Rotated Preference Optimization (RoPO) method, which merely conducts rotational and magnitude-stretching updates on the weight parameters to maintain the hyperspherical energy invariant, thereby preserving the knowledge encoded in the angle between neurons.
Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights.
Towards Flexible Evaluation for Generative Visual Question Answering
Throughout rapid development of multimodal large language models, a crucial ingredient is a fair and accurate evaluation of their multimodal comprehension abilities.
Key-Point-Driven Mathematical Reasoning Distillation of Large Language Model
Distilling LLM mathematical reasoning into Smaller Language Models (SLMs) has emerged as a solution to this challenge, although these smaller models often suffer from errors in calculation and semantic understanding.
Prediction Exposes Your Face: Black-box Model Inversion via Prediction Alignment
Model inversion (MI) attack reconstructs the private training data of a target model given its output, posing a significant threat to deep learning models and data privacy.
Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
However, as the coarse-grained structured pruning poses large damage to the highly interconnected model, achieving a high compression ratio for scaled-up LLMs remains a challenge.
A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
Grounding external knowledge can enhance the factuality of responses in dialogue generation.
Multimodal Table Understanding
Although great progress has been made by previous table understanding methods including recent approaches based on large language models (LLMs), they rely heavily on the premise that given tables must be converted into a certain text sequence (such as Markdown or HTML) to serve as model input.
Think out Loud: Emotion Deducing Explanation in Dialogues
Besides, EDEN can help LLMs achieve better recognition of emotions and causes, which explores a new research direction of explainable emotion understanding in dialogues.
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
The Light-PEFT framework allows for the simultaneous estimation of redundant parameters in both the foundation model and PEFT modules during the early stage of training.
DANCE: Dual-View Distribution Alignment for Dataset Condensation
Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing.
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization
In this paper, we propose DisDiff (Disrupting Diffusion), a novel adversarial attack method to disrupt the diffusion model outputs.
Applying Self-supervised Learning to Network Intrusion Detection for Network Flows with Graph Neural Network
To the best of our knowledge, it is the first GNN-based self-supervised method for the multiclass classification of network flows in NIDS.
Previously on the Stories: Recap Snippet Identification for Story Reading
Similar to the "previously-on" scenes in TV shows, recaps can help book reading by recalling the readers' memory about the important elements in previous texts to better understand the ongoing plot.
Are Large Language Models Table-based Fact-Checkers?
Finally, we analyze some possible directions to promote the accuracy of TFV via LLMs, which is beneficial to further research of table reasoning.
Distilling Mathematical Reasoning Capabilities into Small Language Models
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance.
FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning
We provide convergence analysis based on statistical learning for the federated Newton sketch approaches.
A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification
Whiteness the impressive capabilities in multimodal understanding of Vision Language Foundation Model CLIP a recent two-stage CLIP-based method employs automated prompt engineering to obtain specific textual labels for classifying pedestrians.
ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network
Graph Comparative Learning (GCL) is a self-supervised method that combines the advantages of Graph Convolutional Networks (GCNs) and comparative learning, making it promising for learning node representations.
Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference
Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in multi-turn conversations.
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context.
An Empirical Study of Instruction-tuning Large Language Models in Chinese
This paper will release a powerful Chinese LLMs that is comparable to ChatGLM.
A Survey on Model Compression for Large Language Models
This paper presents a survey of model compression techniques for LLMs.
Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning
Different from existing methods which integrate multiple-granularity features or multiple outputs, we resort to the perspective of representation learning in which auxiliary tasks are utilized to enable the encoder to jointly learn robust features with the main task of per-pixel classification during optimization.
Private Gradient Estimation is Useful for Generative Modeling
In this work, we present a new private generative modeling approach where samples are generated via Hamiltonian dynamics with gradients of the private dataset estimated by a well-trained network.
Combo of Thinking and Observing for Outside-Knowledge VQA
Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features.
Robust Neural Architecture Search
Neural Architectures Search (NAS) becomes more and more popular over these years.
Operation-level Progressive Differentiable Architecture Search
It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.
Improving Differentiable Architecture Search via Self-Distillation
Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.
UATVR: Uncertainty-Adaptive Text-Video Retrieval
In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.
AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification
Consequently, we estimate the size of the spanned space for each category, namely effective area, by detailedly analyzing its samples' distribution.
Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning
In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i. e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion.
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models
Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.
Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering
To this end, we systematically study the design of a training and compression pipeline to search the subnetworks, as well as the assignment of sparsity to different modality-specific modules.
Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension
Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances.
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response.
Handling Label Uncertainty for Camera Incremental Person Re-Identification
Specifically, new data collected from new cameras may probably contain an unknown proportion of identities seen before.
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
However, these models reveal a trade-off that the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data (which is dominated by the biased samples).
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM
In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.
UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection
Recent scene text detection methods are almost based on deep learning and data-driven.
Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge
Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation.
Ranked #1 on
Causal Emotion Entailment
on RECCON
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training
Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.
Sharper Utility Bounds for Differentially Private Models
In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.
Stability and Generalization of Differentially Private Minimax Problems
To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering
Texts in scene images convey critical information for scene understanding and reasoning.
Optical Character Recognition
Optical Character Recognition (OCR)
+4
Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances.
Ranked #50 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem.
Ranked #5 on
Text Spotting
on SCUT-CTW1500
Dense Semantic Contrast for Self-Supervised Visual Representation Learning
Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods.
PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency.
Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images
In this paper, we propose a simple yet effective method for accurate arbitrary-shaped nearby scene text detection.
Check It Again:Progressive Visual Question Answering via Visual Entailment
Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.
Video 3D Sampling for Self-supervised Representation Learning
As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target.
Multi-View Correlation Distillation for Incremental Object Detection
Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data.
MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification
Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes.
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.
Check It Again: Progressive Visual Question Answering via Visual Entailment
Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.
Exploring Instance Relations for Unsupervised Feature Embedding
Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations.
Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.
Rescuing Deep Hashing from Dead Bits Problem
The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods.
Deep Learning for Instance Retrieval: A Survey
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation
It can be regarded as a personalized and interactive emotion recognition task, which is supposed to consider not only the semantic information of text but also the influences from speakers.
Ranked #39 on
Emotion Recognition in Conversation
on IEMOCAP
Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage.
Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection
Inspired by this, we propose a BERT architecture-based model, which concentrates on both intra and inter-modality incongruity for multi-modal sarcasm detection.
Gaussian Constrained Attention Network for Scene Text Recognition
In this paper, we propose Gaussian Constrained Attention Network to deal with this problem.
New Ideas and Trends in Deep Multimodal Content Understanding: A Review
The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
Dirichlet type extensions of Euler sums
In this paper, we study the alternating Euler $T$-sums and $\S$-sums, which are infinite series involving (alternating) odd harmonic numbers, and have similar forms and close relations to the Dirichlet beta functions.
Number Theory
Exploring Relations in Untrimmed Videos for Self-Supervised Learning
Then a designed sampling strategy is used to model relations for video clips.
Two-Level Residual Distillation based Triple Network for Incremental Object Detection
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.
FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection
Accurate detection of multi-oriented text with large variations of scales, orientations, and aspect ratios is of great significance.
Progressive Cluster Purification for Unsupervised Feature Learning
In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.
Neural Architecture Optimization with Graph VAE
The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.
Self-Training for Domain Adaptive Scene Text Detection
To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
Scene text recognition is a hot research topic in computer vision.
Keyphrase Prediction With Pre-trained Language Model
Considering the different characteristics of extractive and generative methods, we propose to divide the keyphrase prediction into two subtasks, i. e., present keyphrase extraction (PKE) and absent keyphrase generation (AKG), to fully exploit their respective advantages.
Nearly Optimal Clustering Risk Bounds for Kernel K-Means
In this paper, we study the statistical properties of kernel $k$-means and obtain a nearly optimal excess clustering risk bound, substantially improving the state-of-art bounds in the existing clustering risk analyses.
Theoretical Analysis of Divide-and-Conquer ERM: Beyond Square Loss and RKHS
However, the studies on learning theory for general loss functions and hypothesis spaces remain limited.
Convolutional Spectral Kernel Learning
Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics.
Data Heterogeneity Differential Privacy: From Theory to Algorithm
Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP).
Input Perturbation: A New Paradigm between Central and Local Differential Privacy
By adding noise to the original training data and training with the `perturbed data', we achieve ($\epsilon$,$\delta$)-differential privacy on the final model, along with some kind of privacy on the original data.
Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.
Ranked #11 on
Self-supervised Video Retrieval
on HMDB51
Ranking and Sampling in Open-Domain Question Answering
Open-domain question answering (OpenQA) aims to answer questions based on a number of unlabeled paragraphs.
Weighted Distributed Differential Privacy ERM: Convex and Non-convex
By detailed theoretical analysis, we show that in distributed setting, the noise bound and the excess empirical risk bound can be improved by considering different weights held by multiple parties.
Semi-supervised Vector-valued Learning: Improved Bounds and Algorithms
Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e. g. multi-task learning and transfer learning.
Automated Spectral Kernel Learning
The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks.
Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.
Towards Sharp Analysis for Distributed Learning with Random Features
In this paper, using refined proof techniques, we first extend the optimal rates for distributed learning with random features to the non-attainable case.
Efficient Cross-Validation for Semi-Supervised Learning
In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF).
Max-Diversity Distributed Learning: Theory and Algorithms
We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning.
Multi-Class Learning: From Theory to Algorithm
In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.
