Search Results for author:
Found 33 papers, 9 papers with code
LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions
Controllable text-to-image generation synthesizes visual text and objects in images with certain conditions, which are frequently applied to emoji and poster generation.
360°REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System
The framework employs a novel 360{\deg} performance assessment method for multi-perspective performance evaluation with fine-grained assessment.
Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game
In this paper, we propose a multi-agent attacker-disguiser game approach to achieve a weak defense mechanism that allows the large model to both safely reply to the attacker and hide the defense intent.
LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification
As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation (DA).
TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features
To get the balance between the computation complexity and memory usage, we propose a new network structure, namely Time-Frequency Domain Mixture Network (TFDMNet), which combines the advantages of both convolution layers and EMLs.
Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference.
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation
POMP involves constructing a directed acyclic meta-graph for each source language, from which we dynamically sample multiple paths to prompt LLMs to mitigate the linguistic noise and improve translations during training.
Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery
Based on the discovered zero-cost proxy, we conduct a ViT architecture search in a training-free manner.
TVT: Training-Free Vision Transformer Search on Tiny Datasets
In this paper, for the first time, we investigate how to search in a training-free manner with the help of teacher models and devise an effective Training-free ViT (TVT) search framework.
GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence
Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility.
Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation.
DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation
To this end, we employ domain adversarial learning as a heuristic neural network initialization method, which can help the meta-learning module converge to a better optimal.
Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification
Theoretically, we prove the convergence of the meta-learning algorithm in MTEM and analyze the effectiveness of MTEM in achieving domain adaptation.
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
In particular, we devise an elaborate search space involving the existing proxies and perform an evolution search to discover the best correlated MQ proxy.
Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain
Prompt learning with large language models (LLMs) has emerged as a recent approach, which designs prompts to lead LLMs to understand the input question and generate the corresponding SQL.
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks
However, most of the mixup methods do not consider the varying degree of learning difficulty in different stages of training and generate new samples with one hot labels, resulting in the model over confidence.
Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval
Text-to-SQL is a task that converts a natural language question into a structured query language (SQL) to retrieve information from a database.
Hashtag-Guided Low-Resource Tweet Classification
Social media classification tasks (e. g., tweet sentiment analysis, tweet stance detection) are challenging because social media posts are typically short, informal, and ambiguous.
RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies
In this paper, we propose Ranking Distillation one-shot NAS (RD-NAS) to enhance ranking consistency, which utilizes zero-cost proxies as the cheap teacher and adopts the margin ranking loss to distill the ranking knowledge.
Progressive Meta-Pooling Learning for Lightweight Image Classification Model
Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field.
StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer
Since cycle construction helps to improve the style transfer ability of the model by rebuilding transferred sentences back to original-style sentences, it brings about a content loss in unsupervised text style transfer tasks.
Semi-Supervised Lifelong Language Learning
In this paper, we explore a novel setting, semi-supervised lifelong language learning (SSLL), where a model learns sequentially arriving language tasks with both labeled and unlabeled data.
Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model
The question is answered in our work with the concept of model calibration; we view a teacher model not only as a source of knowledge but also as a gauge to detect miscalibration of a student.
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems.
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available.
SeqPATE: Differentially Private Text Generation via Knowledge Distillation
Differentially private (DP) learning algorithms provide guarantees on identifying the existence of a training sample from model outputs.
Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization
A common approach is to map a given sentence to content representation that is free of style, and the content representation is fed to a decoder with a target style.
Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network.
Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
Dialogue generation models face the challenge of producing generic and repetitive responses.
Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
In previous work, the external document is utilized by (1) creating a context-aware document memory that integrates information from the document and the conversational context, and then (2) generating responses referring to the memory.
Learning to Abstract for Memory-augmented Conversational Response Generation
In this work, we propose a memory-augmented generative model, which learns to abstract from the training corpus and saves the useful information to the memory to assist the response generation.
Diversifying Neural Conversation Model with Maximal Marginal Relevance
However, traditional seq2seq suffer from a severe weakness: during beam search decoding, they tend to rank universal replies at the top of the candidate list, resulting in the lack of diversity among candidate replies.
How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models
Generative conversational systems are attracting increasing attention in natural language processing (NLP).
