Search Results for author:
Found 109 papers, 58 papers with code
MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation
Diffusion models have shown excellent performance in text-to-image generation.
MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender
Large language models (LLMs), known for their comprehension capabilities and extensive knowledge, have been increasingly applied to recommendation systems (RS).
Rankformer: A Graph Transformer for Recommendation based on Ranking Objective
Although personalized ranking is a fundamental aspect of RS, this critical property is often overlooked in the design of model architectures.
Recent Advances on Generalizable Diffusion-generated Image Detection
To bridge this gap, we present a systematic survey of recent advances and classify them into two main categories: (1) data-driven detection and (2) feature-driven detection.
FlowAgent: Achieving Compliance and Flexibility for Workflow Agents
Experiments on three datasets demonstrate that FlowAgent not only adheres to workflows but also effectively manages OOW queries, highlighting its dual strengths in compliance and flexibility.
Uncertainty-Aware Graph Structure Learning
Importantly, UnGSL serves as a plug-in module that can be seamlessly integrated into existing GSL methods with minimal additional computational cost.
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes.
BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation
To this end, we propose BloomScene, a lightweight structured 3D Gaussian splatting for crossmodal scene generation, which creates diverse and high-quality 3D scenes from text or image inputs.
Future-Conditioned Recommendations with Multi-Objective Controllable Decision Transformer
Our empirical findings emphasize the controllable recommendation strategy's ability to produce item sequences according to different objectives while maintaining performance that is competitive with current recommendation strategies across various objectives.
Position-aware Graph Transformer for Recommendation
Collaborative recommendation fundamentally involves learning high-quality user and item representations from interaction data.
Universal Inceptive GNNs by Eliminating the Smoothness-generalization Dilemma
Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains, such as transaction and social net-works.
The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
Based on our observations, we propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities.
Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data
GDC utilizes a causal disentangle module to separate unit features into adjustment and confounder representations.
Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning
Specifically, we propose a fine-grained representation factorization module that sufficiently extracts valuable sentiment information by factorizing modality into sentiment-relevant and modality-specific representations through crossmodal translation and sentiment semantic reconstruction.
PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
To address these issues, this work extends SL to a new family of loss functions, termed Pairwise Softmax Loss (PSL), which replaces the exponential function in SL with other appropriate activation functions.
From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
Hallucinations in large vision-language models (LVLMs) are a significant challenge, i. e., generating objects that are not presented in the visual input, which impairs their reliability.
Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level
Large language models (LLMs) have demonstrated immense utility across various industries.
Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
Our theoretical results demonstrate that HopeDGN can achieve expressive power equivalent to the 2-DWL test.
The Devil is in the Sources! Knowledge Enhanced Cross-Domain Recommendation in an Information Bottleneck Perspective
To address this concern, in this paper, we propose a novel knowledge enhanced cross-domain recommendation framework named CoTrans, which remolds the core procedures of CDR models with: Compression on the knowledge from the source domain and Transfer of the purity to the target domain.
Conditional Image Synthesis with Diffusion Models: A Survey
In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, i. e., the denoising network and the sampling process.
Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
Our method employs low-frequency words as triggers, embedding the watermark by replacing their embeddings in the model's word embedding layer with those of specific medical terms.
LLM4DSR: Leveraing Large Language Model for Denoising Sequential Recommendation
However, employing LLMs for denoising in sequential recommendation presents notable challenges: 1) Direct application of pretrained LLMs may not be competent for the denoising task, frequently generating nonsensical responses; 2) Even after fine-tuning, the reliability of LLM outputs remains questionable, especially given the complexity of the denoising task and the inherent hallucinatory issue of LLMs.
Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding
To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process.
Large Vision-Language Models as Emotion Recognizers in Context Awareness
Extensive experiments and analyses demonstrate that LVLMs achieve competitive performance in the CAER task across different paradigms.
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
We categorize noise into pointwise noise, which includes low-quality data points, and pairwise noise, which encompasses erroneous data pair associations that affect preference rankings.
SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules
To mitigate the high loading overhead of LoRA serving, SwiftDiffusion employs a bounded asynchronous LoRA loading (BAL) technique, allowing LoRA loading to overlap with the initial base model execution by up to k steps without compromising image quality.
Skip and Skip: Segmenting Medical Images with Prompts
Most medical image lesion segmentation methods rely on hand-crafted accurate annotations of the original image for supervised learning.
CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation
Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasing attention.
Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
To bridge this gap, we introduce Med-HallMark, the first benchmark specifically designed for hallucination detection and evaluation within the medical multimodal domain.
Motif-driven Subgraph Structure Learning for Graph Classification
Notably, applying node-level GSL to graph classification is non-trivial due to the lack of find-grained guidance for intricate structure learning.
Better Late Than Never: Formulating and Benchmarking Recommendation Editing
This paper introduces a novel and significant task termed recommendation editing, which focuses on modifying known and unsuitable recommendation behaviors.
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild.
Towards Scalable Automated Alignment of LLMs: A Survey
Alignment is the most critical step in building large language models (LLMs) that meet human needs.
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective.
PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
In the parameter-efficient secondary SFT phase, a mixture of universal-specific experts strategy is presented to resolve the competency conflict between medical generalist and pediatric expertise mastery.
Revisiting the Message Passing in Heterophilous Graph Neural Networks
Based on HTMP and empirical analysis, we reveal that the success of message passing in existing HTGNNs is attributed to implicitly enhancing the compatibility matrix among classes.
Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance.
Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models
In the realm of Medical Visual Language Models (Med-VLMs), the quest for universal efficient fine-tuning mechanisms remains paramount, especially given researchers in interdisciplinary fields are often extremely short of training resources, yet largely unexplored.
Medical Visual Question Answering
parameter-efficient fine-tuning
+2
How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
Building on these insights, we propose a novel debiasing strategy that leverages a spectral norm regularizer to penalize the magnitude of the principal singular value.
SIGformer: Sign-aware Graph Transformer for Recommendation
Integrating both positive and negative feedback to form a signed graph can lead to a more comprehensive understanding of user preferences.
FaceCat: Enhancing Face Recognition Security with a Unified Diffusion Model
Face anti-spoofing (FAS) and adversarial detection (FAD) have been regarded as critical technologies to ensure the safety of face recognition systems.
Few-shot Named Entity Recognition via Superposition Concept Discrimination
Then a superposition instance retriever is applied to retrieve corresponding instances of these superposition concepts from large-scale text corpus.
Can LLMs' Tuning Methods Work in Medical Multimodal Domain?
In this paper, we delve into the fine-tuning methods of LLMs and conduct extensive experiments to investigate the impact of fine-tuning methods for large models on the existing multimodal model in the medical domain from the training data level and the model structure level.
Debiased Multimodal Understanding for Human Language Sequences
Human multimodal language understanding (MLU) is an indispensable component of expression analysis (e. g., sentiment or humor) from heterogeneous modalities, including visual postures, linguistic contents, and acoustic behaviours.
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
However, current interactions between IR systems and LLMs remain limited, with LLMs merely serving as part of components within IR systems, and IR systems being constructed independently of LLMs.
EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems
EasyRL4Rec seeks to facilitate the model development and experimental process in the domain of RL-based RSs.
Distributionally Robust Graph-based Recommendation System
DR-GNN addresses two core challenges: 1) To enable DRO to cater to graph data intertwined with GNN, we reinterpret GNN as a graph smoothing regularizer, thereby facilitating the nuanced application of DRO; 2) Given the typically sparse nature of recommendation data, which might impede robust optimization, we introduce slight perturbations in the training distribution to expand its support.
Knowledge Translation: A New Pathway for Model Compression
Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead.
MISS: A Generative Pretraining and Finetuning Approach for Med-VQA
Medical visual question answering (VQA) is a challenging multimodal task, where Vision-Language Pre-training (VLP) models can effectively improve the generalization performance.
BSL: Understanding and Improving Softmax Loss for Recommendation
Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research.
How Robust is Google's Bard to Adversarial Image Attacks?
By attacking white-box surrogate vision encoders or MLLMs, the generated adversarial examples can mislead Bard to output wrong image descriptions with a 22% success rate based solely on the transferability.
Benchmarking Large Language Models in Retrieval-Augmented Generation
In this paper, we systematically investigate the impact of Retrieval-Augmented Generation on large language models.
CDR: Conservative Doubly Robust Learning for Debiased Recommendation
In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data.
Homophily-enhanced Structure Learning for Graph Clustering
Graph clustering is a fundamental task in graph analysis, and recent advances in utilizing graph neural networks (GNNs) have shown impressive results.
AdvFAS: A robust face anti-spoofing framework against adversarial examples
Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation
Through theoretical analyses, we find that the conservatism of existing methods fails in pursuing users' long-term satisfaction.
OpenGSL: A Comprehensive Benchmark for Graph Structure Learning
Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption.
How Graph Convolutions Amplify Popularity Bias for Recommendation?
Through theoretical analyses, we identify two fundamental factors: (1) with graph convolution (\textit{i. e.,} neighborhood aggregation), popular items exert larger influence than tail items on neighbor users, making the users move towards popular items in the representation space; (2) after multiple times of graph convolution, popular items would affect more high-order neighbors and become more influential.
Learning In-context Learning for Named Entity Recognition
M}$, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i. e., $\mathcal{ (\lambda .
Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models
Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities.
Life Regression based Patch Slimming for Vision Transformers
In this study, we tackle the patch slimming problem from a different perspective by proposing a life regression module that determines the lifespan of each image patch in one go.
Adap-$τ$: Adaptively Modulating Embedding Magnitude for Recommendation
Recent years have witnessed the great successes of embedding-based methods in recommender systems.
FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion
Specifically, they suffer from two main limitations: 1) existing Graph Convolutional Network (GCN) methods in hyperbolic space rely on tangent space approximation, which would incur approximation error in representation learning, and 2) due to the lack of inner product operation definition in hyperbolic space, existing methods can only measure the plausibility of facts (links) with hyperbolic distance, which is difficult to capture complex data patterns.
On the Theories Behind Hard Negative Sampling for Recommendation
Secondly, we prove that OPAUC has a stronger connection with Top-K evaluation metrics than AUC and verify it with simulation experiments.
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples.
Robust Sequence Networked Submodular Maximization
The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology.
Unbiased Knowledge Distillation for Recommendation
Traditional solutions first train a full teacher model from the training data, and then transfer its knowledge (\ie \textit{soft labels}) to supervise the learning of a compact student model.
KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos
To facilitate model learning, we further collect rich features of users and items as well as users' behavior history.
A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions
Motivated by the tremendous success of deep learning in clustering, one of the most fundamental machine learning tasks, and the large number of recent advances in this direction, in this paper we conduct a comprehensive survey on deep clustering by proposing a new taxonomy of different state-of-the-art approaches.
Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding
Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention.
BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
Combining this novel perspective of two-stage synthesis with advanced generative models (i. e., the diffusion models), the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples.
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset.
Ranked #1 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance
Based on this inspiration, we investigate the domain-invariant unweighted sparse associative structures and the domain-variant strengths of the structures.
CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System
The basic idea is to first learn a causal user model on historical data to capture the overexposure effect of items on user satisfaction.
Few-shot Named Entity Recognition with Self-describing Networks
In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set.
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
The progress of recommender systems is hampered mainly by evaluation as it requires real-time interactions between humans and systems, which is too laborious and expensive.
IHGNN: Interactive Hypergraph Neural Network for Personalized Product Search
On this basis, we develop a specific interactive hypergraph neural network to explicitly encode the structure information (i. e., collaborative signal) into the embedding process.
Neighboring Backdoor Attacks on Graph Convolutional Network
To address such a challenge, we set the trigger as a single node, and the backdoor is activated when the trigger node is connected to the target node.
On the Effectiveness of Sampled Softmax Loss for Item Recommendation
In this work, we aim to offer a better understanding of SSM for item recommendation.
Speech-T: Transducer for Text to Speech and Beyond
Experiments on LJSpeech datasets demonstrate that Speech-T 1) is more robust than the attention based autoregressive TTS model due to its inherent monotonic alignments between text and speech; 2) naturally supports streaming TTS with good voice quality; and 3) enjoys the benefit of joint modeling TTS and ASR in a single network.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription
Considering that there is a large amount of ASR training data, a straightforward method is to leverage ASR data to enhance ALT training.
Automatic Lyrics Transcription
Automatic Speech Recognition
+3
Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
To sufficiently exploit such important information for recommendation, it is essential to disentangle the benign popularity bias caused by item quality from the harmful popularity bias caused by conformity.
Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention
In this paper, we identify and solve the trigger curse problem in few-shot event detection (FSED) from a causal view.
InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction
For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT imaging geometry constraint is not fully embedded into the network during training, leaving room for further performance improvement; 2) the model interpretability is lack of sufficient consideration.
DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network
Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks.
MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition
This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition.
Distilling Holistic Knowledge with Graph Neural Networks
The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner.
Time-aware Path Reasoning on Knowledge Graph for Recommendation
In this work, we propose a novel Time-aware Path reasoning for Recommendation (TPRec for short) method, which leverages the potential of temporal information to offer better recommendation with plausible explanations.
Single-shot structured illumination microscopy
In this paper, we report a novel technique termed single-shot SIM, to overcome these limitations.
Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint
In practical applications, the outdoor weather and illumination are changeable, e. g., cloudy and nighttime, which results in a significant drop of semantic segmentation accuracy of CNN only trained with daytime data.
CausCF: Causal Collaborative Filtering for RecommendationEffect Estimation
It is based on the idea that similar users not only have a similar taste on items, but also have similar treatment effect under recommendations.
AutoDebias: Learning to Debias for Recommendation
This provides a valuable opportunity to develop a universal solution for debiasing, e. g., by learning the debiasing parameters from data.
A General Framework for Learning Prosodic-Enhanced Representation of Rap Lyrics
Learning and analyzing rap lyrics is a significant basis for many web applications, such as music recommendation, automatic music categorization, and music information retrieval, due to the abundant source of digital music in the World Wide Web.
GCF-Net: Gated Clip Fusion Network for Video Action Recognition
These models are trained by applying a deep CNN on single clip of fixed temporal length.
Time Series Domain Adaptation via Sparse Associative Structure Alignment
To reduce the difficulty in the discovery of causal structure, we relax it to the sparse associative structure and propose a novel sparse associative structure alignment model for domain adaptation.
SamWalker++: recommendation with informative sampling strategy
However, the social network information may not be available in many recommender systems, which hinders application of SamWalker.
CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation
To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling.
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
Existing work addresses this issue with Inverse Propensity Weighting (IPW), which decreases the impact of popular items on the training and increases the impact of long-tail items.
On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
The original design of Graph Convolution Network (GCN) couples feature transformation and neighborhood aggregation for node representation learning.
Bias and Debias in Recommender System: A Survey and Future Directions
This motivates us to provide a systematic survey of existing work on RS biases.
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
To tackle the difficulty of singing modeling caused by high sampling rate (wider frequency band and longer waveform), we introduce multi-scale adversarial training in both the acoustic model and vocoder to improve singing modeling.
Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition
Empirical results confirm the efficiency and effectiveness of residual frames as well as the proposed pseudo-3D convolution module.
Generative Adversarial Networks for Video-to-Video Domain Adaptation
Two colonoscopic datasets from different centres, i. e., CVC-Clinic and ETIS-Larib, are adopted to evaluate the performance of domain adaptation of our VideoGAN.
Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback
A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence.
A Cyclically-Trained Adversarial Network for Invariant Representation Learning
Specifically, we propose a cyclically-trained adversarial network to learn a mapping from image space to latent representation space and back such that the latent representation is invariant to a specified factor of variation (e. g., identity).
VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition
Reliable facial expression recognition plays a critical role in human-machine interactions.
Facial Expression Recognition
Facial Expression Recognition (FER)
+4
Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos.
Building A Large Concept Bank for Representing Events in Video
In this paper, we propose to build Concept Bank, the largest concept library consisting of 4, 876 concepts specifically designed to cover 631 real-world events.
