Search Results for author:
Found 306 papers, 116 papers with code
Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer
In this paper, we propose a collaborative learning framework for unsupervised text style transfer using a pair of bidirectional decoders, one decoding from left to right while the other decoding from right to left.
Exploring Non-Autoregressive Text Style Transfer
In this paper, we explore Non-AutoRegressive (NAR) decoding for unsupervised text style transfer.
Conditional Causal Relationships between Emotions and Causes in Texts
The causal relationships between emotions and causes in text have recently received a lot of attention.
Task-oriented Domain-specific Meta-Embedding for Text Classification
Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks.
Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
Large language models (LLMs) often struggle with knowledge-intensive tasks due to a lack of background knowledge and a tendency to hallucinate.
LEO-VL: Towards 3D Vision-Language Generalists via Data Scaling with Efficient Representation
A key obstacle to developing 3D-VL generalists lies in data scalability, hindered by the lack of an efficient scene representation.
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
Manual slide creation is labor-intensive and requires expert prior knowledge.
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes
However, grounding referring expressions beyond objects in 3D scenes remains unexplored.
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
Using CoQuIR, we benchmark 23 retrieval models, covering both open-source and proprietary systems, and find that even top-performing models frequently fail to distinguish buggy or insecure code from their more robust counterparts.
When Large Multimodal Models Confront Evolving Knowledge:Challenges and Pathways
Previous work focused on constructing textual knowledge datasets and exploring knowledge injection in LLMs, lacking exploration of multimodal evolving knowledge injection in LMMs.
Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
Recent advancements in large language models (LLMs) have demonstrated substantial progress in reasoning capabilities, such as DeepSeek-R1, which leverages rule-based reinforcement learning to enhance logical reasoning significantly.
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
In this paper, we introduce the concept of $\textit{safety calibration}$, which systematically addresses both undersafety and oversafety.
Removal of Hallucination on Hallucination: Debate-Augmented RAG
Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a phenomenon we term Hallucination on Hallucination.
EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models
To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries.
Distributed Expectation Propagation for Multi-Object Tracking over Sensor Networks
In this paper, we present a novel distributed expectation propagation algorithm for multiple sensors, multiple objects tracking in cluttered environments.
Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL
Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks.
MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction
The rigid deformation is applied to the motion-related 3DGs for modeling the dynamic, and the attention-based optimization on the motion-related 3DGs enables the reconstruction of the emerging objects.
MSDformer: Multi-scale Discrete Transformer For Time Series Generation
MSDformer employs a multi-scale time series tokenizer to learn discrete token representations at multiple scales, which jointly characterize the complex nature of time series data.
GLProtein: Global-and-Local Structure Aware Protein Representation Learning
We argue that the structural information of proteins is not only limited to their 3D information but also encompasses information from amino acid molecules (local information) to protein-protein structure similarity (global information).
FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
This paper investigates training better visual world models for robot manipulation, i. e., models that can predict future visual observations by conditioning on past frames and robot actions.
Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning
Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes.
Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding
While Large Multimodal Models (LMMs) have demonstrated significant progress in general vision-language (VL) tasks, their performance in emotion-specific scenarios remains limited.
MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans
Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization.
Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent.
GraphATC: advancing multilevel and multi-label anatomical therapeutic chemical classification via atom-level graph learning
The accurate categorization of compounds within the anatomical therapeutic chemical (ATC) system is fundamental for drug development and fundamental research.
Ranked #1 on
Drug ATC Classification
on ATC-SMILES
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks.
SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
In light of this, we propose SemDiff, a novel unrestricted adversarial attack that explores the semantic latent space of diffusion models for meaningful attributes, and devises a multi-attributes optimization approach to ensure attack success while maintaining the naturalness and imperceptibility of generated UAEs.
Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
Specifically, we introduce an LLM-based poison scanner to detect the poisoned items by leveraging the powerful language understanding and rich knowledge of LLMs.
CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
Recently, Large Language Model (LLM)-empowered recommender systems (RecSys) have brought significant advances in personalized user experience and have attracted considerable attention.
Investigating and Mitigating Stereotype-aware Unfairness in LLM-based Recommendations
Large Language Models (LLMs) have demonstrated unprecedented language understanding and reasoning capabilities to capture diverse user preferences and advance personalized recommendations.
Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation
Recently, Large Language Model (LLM)-empowered recommender systems have revolutionized personalized recommendation frameworks and attracted extensive attention.
A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models
With the advancement of web techniques, they have significantly revolutionized various aspects of people's lives.
Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis
Our evaluation of state-of-the-art 3D-VL models on Beacon3D reveals that (i) object-centric evaluation elicits true model performance and particularly weak generalization in QA; (ii) grounding-QA coherence remains fragile in current 3D-VL models, and (iii) incorporating large language models (LLMs) to 3D-VL models, though as a prevalent practice, hinders grounding capabilities and has yet to elevate QA capabilities.
SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs
However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse distribution of Gaussian points and insufficient view supervision.
SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
To address this issue, we introduce SAUCE, a novel method that leverages sparse autoencoders (SAEs) for fine-grained and selective concept unlearning in VLMs.
ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer
In this paper, we comprehensively analyze the limitations of the standard diffusion parameterization, which learns to predict noise, in the context of style transfer.
Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
To address this gap, we introduce RecBench+, a new dataset benchmark designed to access LLMs' ability to handle intricate user recommendation needs in the era of LLMs.
Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification
Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge.
Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior
When encoded brain representations are directly aligned with the corresponding pretrained image features, the System GAP and Random GAP between paired data challenge the model, requiring it to bridge these gaps.
Towards Universal Learning-based Model for Cardiac Image Reconstruction: Summary of the CMRxRecon2024 Challenge
In addition, through a detailed analysis of the results submitted to the challenge, we have also made several findings, including: 1) adaptive prompt-learning embedding is an effective means for achieving strong generalization in reconstruction models; 2) enhanced data consistency based on physics-informed networks is also an effective pathway toward a universal model; 3) traditional evaluation metrics have limitations when assessing ground-truth references with moderate or lower image quality, highlighting the need for subjective evaluation methods.
Calibrating LLM Confidence with Semantic Steering: A Multi-Prompt Aggregation Framework
Large Language Models (LLMs) often exhibit misaligned confidence scores, usually overestimating the reliability of their predictions.
Artificial Intelligence in Reactor Physics: Current Status and Future Prospects
Reactor physics is the study of neutron properties, focusing on using models to examine the interactions between neutrons and materials in nuclear reactors.
MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining from scratch.
HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge
Given that substantial amounts of domain-specific knowledge are stored in structured formats, such as web data organized through HTML, Large Language Models (LLMs) are expected to fully comprehend this structured information to broaden their applications in various real-world downstream tasks.
FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes
Federated Learning (FL) has emerged as an essential framework for distributed machine learning, especially with its potential for privacy-preserving data processing.
A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}.
Cardiac Evidence Backtracking for Eating Behavior Monitoring using Collocative Electrocardiogram Imagining
This is accomplished using a collocative learning framework in which 1) we construct collocative tensors as pseudo-images from 1D ECG signals to improve the feasibility of 2D image-based deep models; 2) we formulate the cardiac logic of analyzing the ECG data in a comparative way as periodic attention regulators so as to guide the deep inference to collect evidence in a human comprehensible manner; and 3) we improve the interpretability of the framework by enabling the backtracking of evidence with a set of methods designed for Class Activation Mapping (CAM) decoding and decision tree/forest generation.
Mean of Means: Human Localization with Calibration-free and Unconstrained Camera Settings (extended version)
Accurate human localization is crucial for various applications, especially in the Metaverse era.
Utilizing Effective Dynamic Graph Learning to Shield Financial Stability from Risk Propagation
Our approach represents a significant advancement in leveraging artificial intelligence to enhance financial stability, offering a powerful solution to mitigate the spread of risks within financial networks.
Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation
Extensive experiments on Spider and BIRD benchmarks verify that KaSLA can significantly improve the SQL generation performance of SOTA Text2SQL models by substituting their schema linking processes.
Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models
Large Language Models (LLMs) have demonstrated impressive capabilities in natural language processing tasks, such as text generation and semantic understanding.
Generating on Generated: An Approach Towards Self-Evolving Diffusion Models
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities.
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
By treating LLMs as knowledge databases, we translate malicious queries in natural language into structured non-natural query language to bypass the safety alignment mechanisms of LLMs.
Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN
In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power.
AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs
In this work, we propose the \methodname{} pipeline for automatically annotating UI elements with detailed functionality descriptions at scale.
Can You Move These Over There? An LLM-based VR Mover for Supporting Object Manipulation
In our daily lives, we can naturally convey instructions for the spatial manipulation of objects using words and gestures.
OneForecast: A Universal Framework for Global and Regional Weather Forecasting
Accurate weather forecasts are important for disaster prevention, agricultural planning, etc.
Synthetic User Behavior Sequence Generation with Large Language Models for Smart Homes
In this paper, we propose an LLM-based synthetic dataset generation IoTGen framework to enhance the generalization of downstream smart home intelligent models.
STAR: Stepwise Task Augmentation and Relation Learning for Aspect Sentiment Quad Prediction
The most challenging task, aspect sentiment quad prediction (ASQP), predicts these elements simultaneously, hindered by difficulties in accurately coupling different sentiment elements.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update
Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs).
Computational Protein Science in the Era of Large Language Models (LLMs)
As a result, researchers have actively introduced LLM techniques in computational protein science, developing protein Language Models (pLMs) that skillfully grasp the foundational knowledge of proteins and can be effectively generalized to solve a diversity of sequence-structure-function reasoning problems.
Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model
With the growing significance of network security, the classification of encrypted traffic has emerged as an urgent challenge.
Efficient Graph Condensation via Gaussian Process
To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation.
Contrastive Learning Augmented Social Recommendations
To mitigate noise propagation in graph data and extract reliable social interests, we introduce a dual-view denoising framework.
Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements
Graph-level tasks, which predict properties or classes for the entire graph, are critical for applications, such as molecular property prediction and subgraph counting.
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI.
A Survey on Large Language Model Acceleration based on KV Cache Management
This survey provides a comprehensive overview of KV cache management strategies for LLM acceleration, categorizing them into token-level, model-level, and system-level optimizations.
PolySmart and VIREO @ TRECVid 2024 Ad-hoc Video Search
The generated queries retrieve different rank lists from the original query.
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks.
PolySmart @ TRECVid 2024 Video Captioning (VTT)
In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for video content.
PolySmart @ TRECVid 2024 Medical Video Question Answering
Specifically, we provide the video captions generated by the LLaVA-Next-Video model and the video subtitles with timestamps as context, and ask GPT4 to generate step captions for the given medical query.
Score-based Generative Diffusion Models for Social Recommendations
With the prevalence of social networks on online platforms, social recommendation has become a vital technique for enhancing personalized recommendations.
TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation
In this paper, we propose Text-based Open Molecule Generation Benchmark (TOMG-Bench), the first benchmark to evaluate the open-domain molecule generation capability of LLMs.
Ranked #1 on
Description-guided molecule generation
on TOMG-Bench
TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
In this paper, we present TINED, a novel approach that distills GNNs to MLPs on a layer-by-layer basis using Teacher Injection and Dirichlet Energy Distillation techniques.
Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning
Implicit sentiment analysis (ISA) presents significant challenges due to the absence of salient cue words.
Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor
Large multimodal models (LMMs) have shown remarkable performance in the visual commonsense reasoning (VCR) task, which aims to answer a multiple-choice question based on visual commonsense within an image.
MolReFlect: Towards Fine-grained In-Context Alignment between Molecules and Texts
Previous endeavours often treat the molecule as a general SMILES string or molecular graph, neglecting the fine-grained alignments between the molecular sub-structures and the descriptive textual phrases, which are crucial for accurate and explainable predictions.
Ranked #2 on
Text-based de novo Molecule Generation
on ChEBI-20
MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts
Previous endeavours often treat the molecule as a general SMILES string or molecular graph, neglecting the fine-grained alignments between the molecular sub-structures and the descriptive textual phrases, which are crucial for accurate and explainable predictions.
LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems
Transformer models have achieved remarkable success in sequential recommender systems (SRSs).
Efficient and Robust Regularized Federated Recommendation
In user preference modeling, both methods learn local and global models, collaboratively learning users' common and personalized interests under the federated learning setting.
Enhance Hyperbolic Representation Learning via Second-order Pooling
To address this issue, we introduce second-order pooling into hyperbolic representation learning, as it naturally increases the distance between samples without compromising the generalization ability of the input features.
CloudEye: A New Paradigm of Video Analysis System for Mobile Visual Scenarios
Mobile deep vision systems play a vital role in numerous scenarios.
DMVC: Multi-Camera Video Compression Network aimed at Improving Deep Learning Accuracy
We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications.
Towards Ground-truth-free Evaluation of Any Segmentation in Medical Images
We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images).
Autonomous Vehicle Decision-Making Framework for Considering Malicious Behavior at Unsignalized Intersections
In this paper, we propose a Q-learning based decision-making framework to improve the safety and efficiency of Autonomous Vehicles when they encounter other maliciously behaving vehicles while passing through unsignalized intersections.
LATEX-GCL: Large Language Models (LLMs)-Based Data Augmentation for Text-Attributed Graph Contrastive Learning
Graph Contrastive Learning (GCL) is a potent paradigm for self-supervised graph learning that has attracted attention across various application scenarios.
SSD4Rec: A Structured State Space Duality Model for Efficient Sequential Recommendation
Sequential recommendation methods are crucial in modern recommender systems for their remarkable capability to understand a user's changing interests based on past interactions.
CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization
This is based on the insight that appropriate output vectors of the text encoder for the context tokens can only be achieved if the new concept's text embedding is correctly learned.
Self-supervised Topic Taxonomy Discovery in the Box Embedding Space
Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them.
Decentralised Variational Inference Frameworks for Multi-object Tracking on Sensor Networks: Additional Notes
This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges among neighboring sensors.
Reasoning Factual Knowledge in Structured Data with Large Language Models
This benchmark allows us to investigate the capability of LLMs across five factual tasks derived from the unique characteristics of structural facts.
DATTA: Towards Diversity Adaptive Test-Time Adaptation in Dynamic Wild World
It features three key components: Diversity Discrimination (DD) to assess batch diversity, Diversity Adaptive Batch Normalization (DABN) to tailor normalization methods based on DD insights, and Diversity Adaptive Fine-Tuning (DAFT) to selectively fine-tune the model.
Reference-free Hallucination Detection for Large Vision-Language Models
In particular, we conduct an extensive study on three kinds of techniques: uncertainty-based, consistency-based, and supervised uncertainty quantification methods on four representative LVLMs across two different tasks.
A Versatile Framework for Attributed Network Clustering via K-Nearest Neighbor Augmentation
In this paper, we first present AHCKA as an efficient approach to attributed hypergraph clustering (AHC).
Task-oriented Sequential Grounding in 3D Scenes
Grounding natural language in physical 3D environments is essential for the advancement of embodied artificial intelligence.
Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
For image restoration, MCGF incorporates a shared encoder and a lightweight restoration module to help the backbone eliminate weather-specific information.
Joint Universal Adversarial Perturbations with Interpretations
Recent studies have shown that adversaries can manipulate the predictions of DNNs by adding a universal adversarial perturbation (UAP) to benign samples.
A Survey of Mamba
In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel.
LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting
To handle these issues, we propose the LoopSparseGS, a loop-based 3DGS framework for the sparse novel view synthesis task.
Dynamic Universal Approximation Theory: Foundations for Parallelism in Neural Networks
Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks.
Multi-Level Querying using A Knowledge Pyramid
We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall.
Mean of Means: A 10-dollar Solution for Human Localization with Calibration-free and Unconstrained Camera Settings
Accurate human localization is crucial for various applications, especially in the Metaverse era.
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings.
Ranked #3 on
Video Grounding
on QVHighlights
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction.
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing.
Ranked #5 on
Image Editing
on ImgEdit-Data
Backdoor Graph Condensation
However, while existing graph condensation studies mainly focus on the best trade-off between graph size and the GNNs' performance (model utility), they overlook the security issues of graph condensation.
RVISA: Reasoning and Verification for Implicit Sentiment Analysis
To identify implicit sentiment with reliable reasoning, this study proposes RVISA, a two-stage reasoning framework that harnesses the generation ability of DO LLMs and the reasoning ability of ED LLMs to train an enhanced reasoner.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
Dynamic Universal Approximation Theory: The Basic Theory for Deep Learning-Based Computer Vision Models
What is the fundamental difference between residual-based CNNs and Transformer-based networks?
Dynamic Universal Approximation Theory: The Basic Theory for Transformer-based Large Language Models
Language models have emerged as a critical area of focus in artificial intelligence, particularly with the introduction of groundbreaking innovations like ChatGPT.
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
First, we introduce a self-supervised approach to learn a behavior encoder that produces discretized tokens for behavior trajectories $\tau = \{o_0, a_0, \dots\}$ and an imitation learning policy decoder conditioned on these tokens.
Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask
However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors.
TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation
There is a growing interest in utilizing large-scale language models (LLMs) to advance next-generation Recommender Systems (RecSys), driven by their outstanding language understanding and in-context learning capabilities.
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
We attribute these issues to the incorrect learning of the embedding alignment for the concept.
FIRM: Flexible Interactive Reflection reMoval
Secondly, we devise a contrastive mask-guided reflection removal network that comprises a newly proposed contrastive guidance interaction block (CGIB).
MGCP: A Multi-Grained Correlation based Prediction Network for Multivariate Time Series
Multivariate time series prediction is widely used in daily life, which poses significant challenges due to the complex correlations that exist at multi-grained levels.
Expert-Guided Extinction of Toxic Tokens for Debiased Generation
Large language models (LLMs) can elicit social bias during generations, especially when inference with toxic prompts.
Entity Alignment with Noisy Annotations from Large Language Models
Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs.
Unifying 3D Vision-Language Understanding via Promptable Queries
A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene.
Ranked #10 on
3D Question Answering (3D-QA)
on SQA3D
Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features
This paper investigates the dynamics of a deep neural network (DNN) learning interactions.
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
Given the powerful abilities of RAG in providing the latest and helpful auxiliary information, Retrieval-Augmented Large Language Models (RA-LLMs) have emerged to harness external and authoritative knowledge bases, rather than solely relying on the model's internal knowledge, to augment the generation quality of LLMs.
A Survey on Personalized Content Synthesis with Diffusion Models
This paper offers a comprehensive survey of PCS, with a particular focus on the diffusion models.
Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation
The proposed algorithm compresses the cluttered raw retrieved documents into a compact set of crucial concepts distilled from the informative nodes of AMR by referring to reliable linguistic features.
Abstract Meaning Representation
Open-Domain Question Answering
+3
SlotGAT: Slot-based Message Passing for Heterogeneous Graph Neural Network
We identify a potential semantic mixing issue in existing message passing processes, where the representations of the neighbors of a node $v$ are forced to be transformed to the feature space of $v$ for aggregation, though the neighbors are in different types.
Graph Machine Learning in the Era of Large Language Models (LLMs)
Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.
CLIP-GS: CLIP-Informed Gaussian Splatting for Real-time and View-consistent 3D Semantic Understanding
Additionally, to address the semantic ambiguity, caused by utilizing view-inconsistent 2D CLIP semantics to supervise Gaussians, we introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.
MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets
Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance.
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns.
Automated discovery of symbolic laws governing skill acquisition from naturally occurring data
Skill acquisition is a key area of research in cognitive psychology as it encompasses multiple psychological processes.
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual statements.
A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning
The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images.
Generative Active Learning for Image Synthesis Personalization
The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept.
Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting
Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features from pre-trained image encoders into a novel semantic component of 3D Gaussians, which is based on spatial relationship and need no additional training.
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies.
VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos.
FashionReGen: LLM-Empowered Fashion Report Generation
Fashion analysis refers to the process of examining and evaluating trends, styles, and elements within the fashion industry to understand and interpret its current state, generating fashion reports.
Large Language Models are In-Context Molecule Learners
Large Language Models (LLMs) have demonstrated exceptional performance in biochemical tasks, especially the molecule caption translation task, which aims to bridge the gap between molecules and natural language texts.
HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative
Based on HoloVIC, we formulated four tasks to facilitate the development of related research.
Linear-Time Graph Neural Networks for Scalable Recommendations
In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy.
One Train for Two Tasks: An Encrypted Traffic Classification Framework Using Supervised Contrastive Learning
In particular, we utilize supervised contrastive learning to enhance the packet-level and flow-level representations and perform graph data augmentation on the byte-level traffic graph so that the fine-grained semantic-invariant characteristics between bytes can be captured through contrastive learning.
OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding
Second, from the cross-view perspective, we propose a Cross-view Self-enhancement (CSE) strategy to address the challenge raised by view-inconsistent semantics.
Progress and Opportunities of Foundation Models in Bioinformatics
Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.
Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey
Large-scale pre-trained vision models (PVMs) have shown great potential for adaptability across various downstream vision tasks.
SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition
3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed.
One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
During the gradient descent learning, a one-step forward search is designed to find the trial gradient of the next-step, which is adopted to adjust the gradient of current step towards the direction of fast convergence.
3D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Field
One of the innovative features of Du-NeRF is that it decouples a view-independent component from the density field and uses it as a label to supervise the learning process of the SDF field.
PSAvatar: A Point-based Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splatting
In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering.
SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data.
Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering
Central to our focus is the utilizing of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements.
3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework
Comparative evaluations with popular point-based methods on HPoint103 and the public dataset DHP19 demonstrate the dramatic outperformance of our D-CPT.
Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
Experiments show that QST can reduce the total memory footprint by up to 2. 3 $\times$ and speed up the finetuning process by up to 3 $\times$ while achieving competent performance compared with the state-of-the-art.
Cross Initialization for Face Personalization of Text-to-Image Models
Additionally a fast version of our method allows for capturing an input image in roughly 26 seconds while surpassing the baseline methods in terms of both reconstruction and editability.
Cross Initialization for Personalized Text-to-Image Generation
Additionally, a fast version of our method allows for capturing an input image in roughly 26 seconds, while surpassing the baseline methods in terms of both reconstruction and editability.
CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update
However, these methods often overlook the potential for continual learning, typically by freezing the utilized tools, thus limiting their adaptation to environments requiring new knowledge.
Compositional Inversion for Stable Diffusion Models
It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space.
Recognizing Conditional Causal Relationships about Emotions and Their Corresponding Conditions
To highlight the context in such special causal relationships, we propose a new task to determine whether or not an input pair of emotion and cause has a valid causal relationship under different contexts and extract the specific context clauses that participate in the causal relationship.
Exploring Causal Learning through Graph Neural Networks: An In-depth Review
In machine learning, exploring data correlations to predict outcomes is a fundamental task.
An Embodied Generalist Agent in 3D World
However, several significant challenges remain: (i) most of these models rely on 2D images yet exhibit a limited capacity for 3D input; (ii) these models rarely explore the tasks inherently defined in 3D world, e. g., 3D grounding, embodied reasoning and acting.
Multi-agent Attacks for Black-box Social Recommendations
To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance.
NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function
Specifically, we introduce loss functions to facilitate query points to iteratively reach the moving targets and aggregate onto the approximated surface, thereby learning a global surface representation of the data.
Embedding in Recommender Systems: A Survey
This survey covers embedding methods like collaborative filtering, self-supervised learning, and graph-based techniques.
Fast Graph Condensation with Structure-based Neural Tangent Kernel
The rapid development of Internet technology has given rise to a vast amount of graph-structured data.
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems.
Ranked #3 on
Visual Reasoning
on Bongard-OpenWorld
TF-DCon: Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation
Notably, the condensation paradigm of this method is forward and free from iterative optimization on the synthesized dataset.
Multi-Scale Spatial-Temporal Recurrent Networks for Traffic Flow Prediction
Traffic flow prediction is one of the most fundamental tasks of intelligent transportation systems.
Label Supervised LLaMA Finetuning
We evaluate this approach with Label Supervised LLaMA (LS-LLaMA), based on LLaMA-2-7B, a relatively small-scale LLM, and can be finetuned on a single GeForce RTX4090 GPU.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL03
(F1 (micro) metric)
Dataset Condensation for Recommendation
Specifically, we model the discrete user-item interactions via a probabilistic approach and design a pre-augmentation module to incorporate the potential preferences of users into the condensed datasets.
Enhancing Graph Collaborative Filtering via Uniformly Co-Clustered Intent Modeling
To model the compatibility between user intents and item properties, we design the user-item co-clustering module, maximizing the mutual information of co-clusters of users and items.
FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning
These issues compromise both the accuracy and the computational efficiency of models in both Machine Learning and Unlearning.
Neural Gradient Learning and Optimization for Oriented Point Normal Estimation
We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation.
Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs
For example, on a Bitcoin dataset with 20 million nodes and 203 million edges, DIAM attains an F1 score of 96. 55%, markedly surpassing the runner-up's score of 83. 92%.
Variational Tracking and Redetection for Closely-spaced Objects in Heavy Clutter: Supplementary Materials
The non-homogeneous Poisson process (NHPP) is a widely used measurement model that allows for an object to generate multiple measurements over time.
Consensus-based Distributed Variational Multi-object Tracker in Multi-Sensor Network
Then, we develop a distributed version leveraging the average consensus algorithm, which is theoretically equivalent to the centralised sensor fusion tracker and requires only local message passing with neighbouring sensors.
LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following
E-commerce authoring entails creating engaging, diverse, and targeted content to enhance preference elicitation and retrieval experience.
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment
3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence.
Ranked #7 on
3D Question Answering (3D-QA)
on SQA3D
DiffusePast: Diffusion-based Generative Replay for Class Incremental Semantic Segmentation
The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes.
TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification
Encrypted traffic classification is receiving widespread attention from researchers and industrial companies.
Certified Robustness for Large Language Models with Self-Denoising
This largely falls into the study of certified robust LLMs, i. e., all predictions of LLM are certified to be correct in a local region around the input.
Counterfactual Explanation for Fairness in Recommendation
The counterfactual explanations help to provide rational and proximate explanations for model fairness, while the attentive action pruning narrows the search space of attributes.
Recommender Systems in the Era of Large Language Models (LLMs)
As a result, recent studies have attempted to harness the power of LLMs to enhance recommender systems.
Identification of Causal Relationship between Amyloid-beta Accumulation and Alzheimer's Disease Progression via Counterfactual Inference
Alzheimer's disease (AD) is a neurodegenerative disorder that is beginning with amyloidosis, followed by neuronal loss and deterioration in structure, function, and cognition.
STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Prediction
However, a survey study of graph learning, spatial-temporal graph models for traffic, as well as a fair comparison of baseline models are pending and unavoidable issues.
Farthest Streamline Sampling for the Uniform Distribution of Forearm Muscle Fiber Tracts from Diffusion Tensor Imaging
FSS reduced the sampling of long tracts (10% reduction in fiber length, P<0. 05), and the architectural parameters were within physiological ranges (two parameters with P<0. 05).
Recurrent Attention Networks for Long-text Modeling
Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention.
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective
In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning.
Ranked #5 on
Text-based de novo Molecule Generation
on ChEBI-20
FERN: Leveraging Graph Attention Networks for Failure Evaluation and Robust Network Design
By providing a neural network function approximation of this common kernel using graph attention networks, we develop a unified learning-based framework, FERN, for scalable Failure Evaluation and Robust Network design.
Inferring Attracting Basins of Power System with Machine Learning
Power systems dominated by renewable energy encounter frequently large, random disturbances, and a critical challenge faced in power-system management is how to anticipate accurately whether the perturbed systems will return to the functional state after the transient or collapse.
Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation
In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner.
Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models.
Unlocking the Power of GANs in Non-Autoregressive Text Generation
Generative Adversarial Networks (GANs) have been studied in text generation to tackle the exposure bias problem.
A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairness
The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset.
MD-Manifold: A Medical-Distance-Based Representation Learning Approach for Medical Concept and Patient Representation
Representing medical concepts for healthcare analytical tasks requires incorporating medical domain knowledge and prior information from patient description data.
Attention-based Spatial-Temporal Graph Convolutional Recurrent Networks for Traffic Forecasting
The key challenge is to effectively model complex spatial-temporal dependencies and correlations in modern traffic data.
Dynamic Graph Convolutional Network with Attention Fusion for Traffic Flow Prediction
Accurate and real-time traffic state prediction is of great practical importance for urban traffic control and web mapping services.
Fairly Adaptive Negative Sampling for Recommendations
Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i. e., clicked by a user) and negative items (i. e., obtained by negative sampling).
