Search Results for author:
Found 52 papers, 18 papers with code
AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets.
Physics-Informed LLM-Agent for Automated Modulation Design in Power Electronics Systems
LLM-based autonomous agents have demonstrated outstanding performance in solving complex industrial tasks.
A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications
With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical.
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
Then, this teacher model guides the large-scale poisoned student model in unlearning the backdoor, leveraging PEFT.
Weak-to-Strong Backdoor Attack for Large Language Models
Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks.
A Grey-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse
Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have revolutionized image synthesis and manipulation.
Decoder Pre-Training with only Text for Scene Text Recognition
Extensive experiments across various STR decoders and language recognition tasks underscore the broad applicability and remarkable performance of DPTR, providing a novel insight for STR pre-training.
A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings.
Cluster-based Graph Collaborative Filtering
This model performs high-order graph convolution on cluster-specific graphs, which are constructed by capturing the multiple interests of users and identifying the common interests among them.
Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training
For the last-$k$ words test with OpenLLaMA-3B, 11 out of 16 users, with an average of 24 examples each, successfully identify their data from 1. 8M examples.
PE-GPT: A Physics-Informed Interactive Large Language Model for Power Converter Modulation Design
This paper proposes PE-GPT, a custom-tailored large language model uniquely adapted for power converter modulation design.
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Motivated by this insight, we developed a Poisoned Sample Identification Module (PSIM) leveraging PEFT, which identifies poisoned samples through confidence, providing robust defense against weight-poisoning backdoor attacks.
Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Our studies demonstrate that an attacker can manipulate the behavior of large language models by poisoning the demonstration context, without the need for fine-tuning the model.
Focus on Local Regions for Query-based Object Detection
We improve the self-attention by isolating connections between irrelevant objects that makes it focus on local regions but not global regions.
A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation
Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels.
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Given a single test sample, the VLM is forced to maximize the CLIP reward between the input and sampled results from the VLM output distribution.
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
With such merits, we transform CLIP into a scene text reader and introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP.
Ranked #1 on
Scene Text Recognition
on Uber-Text
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
Our method does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack.
Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding
To mitigate this issue, parameter-efficient transfer learning algorithms, such as adapters and prefix tuning, have been proposed as a way to introduce a few trainable parameters that can be plugged into large pre-trained language models such as BERT, and HuBERT.
Physics-Informed Neural Networks for Prognostics and Health Management of Lithium-Ion Batteries
Physics-Informed Neural Network (PINN) is an efficient tool to fuse empirical or physical dynamic models with data-driven models.
AutoPINN: When AutoML Meets Physics-Informed Neural Networks
We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.
A Transformer-Based Substitute Recommendation Model Incorporating Weakly Supervised Customer Behavior Data
The substitute-based recommendation is widely used in E-commerce to provide better alternatives to customers.
Generative Prompt Tuning for Relation Classification
Current prompt tuning methods mostly convert the downstream tasks to masked language modeling problems by adding cloze-style phrases and mapping all labels to verbalizations with fixed length, which has proven effective for tasks with simple label spaces.
Ranked #2 on
Relation Extraction
on Re-TACRED
Slimmable Networks for Contrastive Self-supervised Learning
In this work, we introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers, namely, slimmable networks for contrastive self-supervised learning (SlimCLR).
A Step-by-Step Gradient Penalty with Similarity Calculation for Text Summary Generation
The summary generation model equipped with gradient penalty avoids overfitting and makes the model more stable.
Ranked #1 on
Abstractive Text Summarization
on EDUsum
Latent Heterogeneous Graph Network for Incomplete Multi-View Learning
Multi-view learning has progressed rapidly in recent years.
Learning Personalized Representations using Graph Convolutional Network
Then we propose a graph convolutional network(GCN) based model, namely Personalized Dynamic Routing Feature Encoder(PDRFE), that generates personalized customer representations learned from the built graph.
Analyzing Modality Robustness in Multimodal Sentiment Analysis
In this work, we hope to address that by (i) Proposing simple diagnostic checks for modality robustness in a trained multimodal model.
Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)
Few-shot relation learning refers to infer facts for relations with a limited number of observed triples.
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
In this paper, to reduce the number of redundant video tokens, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones.
Ranked #11 on
Video Retrieval
on MSVD
(using extra training data)
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models
The results show that WuDaoMM can be applied as an efficient dataset for VLPMs, especially for the model in text-to-image generation task.
Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.
FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning
Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model to prefer a candidate that is logically consistent with the speaker's history logic.
FGLP: A Federated Fine-Grained Location Prediction System for Mobile Users
The framework runs on the phones of the users and also on a server that coordinates learning from all users in the system.
Attacking Adversarial Attacks as A Defense
In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases.
Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering
Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities.
ES-Net: Erasing Salient Parts to Learn More in Re-Identification
In this paper, we propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image.
Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph
The structural information of Knowledge Bases (KBs) has proven effective to Question Answering (QA).
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
Each of these small networks has a fraction of the original one's parameters.
Ranked #31 on
Image Classification
on CIFAR-100
(using extra training data)
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions.
Multi-Objective Parameter-less Population Pyramid for Solving Industrial Process Planning Problems
Evolutionary methods are effective tools for obtaining high-quality results when solving hard practical problems.
Adversarial-Learned Loss for Domain Adaptation
In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA).
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time.
Region Mutual Information Loss for Semantic Segmentation
In this paper, we develop a region mutual information (RMI) loss to model the dependencies among pixels more simply and efficiently.
Correlation Maximized Structural Similarity Loss for Semantic Segmentation
Inspired by the widely-used structural similarity (SSIM) index in image quality assessment, we use the linear correlation between two images to quantify their structural similarity.
Heavy quark expansion for heavy-light light-cone operators
We generalize the celebrated heavy quark expansion to nonlocal QCD operators.
High Energy Physics - Phenomenology
ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e. g., symmetric contracting and expansive paths as well as lateral skip-connections.
Improving Semantic Segmentation via Dilated Affinity
To be specific, our method explicitly requires the network to predict semantic segmentation as well as dilated affinity, which is a sparse version of pair-wise pixel affinity.
An End-to-End Multi-task Learning Model for Fact Checking
With huge amount of information generated every day on the web, fact checking is an important and challenging task which can help people identify the authenticity of most claims as well as providing evidences selected from knowledge source like Wikipedia.
Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform
Applying Machine Learning (ML) to business applications for automation usually faces difficulties when integrating diverse ML dependencies and services, mainly because of the lack of a common ML framework.
