Search Results for author:
Found 732 papers, 218 papers with code
HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction
In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.
Ranked #6 on
Skeleton Based Action Recognition
on UAV-Human
Unsupervised Multi-View CNN for Salient View Selection of 3D Objects and Scenes
We present an unsupervised 3D deep learning framework based on a ubiquitously true proposition named by us view-object consistency as it states that a 3D object and its projected 2D views always belong to the same object class.
Towards Generalizeable Semantic Product Search by Text Similarity Pre-training on Search Click Logs
Recently, semantic search has been successfully applied to E-commerce product search and the learned semantic space for query and product encoding are expected to generalize well to unseen queries or products.
Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation.
Distributed perception of social power in influence networks with stubborn individuals
We propose two dynamical models for distributed perception of social power based on the Friedkin-Johnsen (FJ) opinion dynamics: one without and one with reflected appraisals.
Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning
Gene selection in high-dimensional genomic data is essential for understanding disease mechanisms and improving therapeutic outcomes.
LPCM: Learning-based Predictive Coding for LiDAR Point Cloud Compression
The predictive geometry coding method in the geometry-based point cloud compression (G-PCC) standard uses the inherent angular resolution to predict the azimuth angles.
Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
By decoupling reasoning from language, latent reasoning promises richer cognitive representations and more flexible, faster inference.
LIFEBench: Evaluating Length Instruction Following in Large Language Models
To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' ability to follow length instructions across diverse tasks and a wide range of specified lengths.
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte Carlo simulations, remain computationally expensive.
KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities.
Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity
Euclidean diffusion models have achieved remarkable success in generative modeling across diverse domains, and they have been extended to manifold case in recent advances.
SpNeRF: Memory Efficient Sparse Volumetric Neural Rendering Accelerator for Edge Devices
The preprocessing step employs hash mapping to support irregular data access while maintaining a minimal memory size.
Efficient and Scalable Neural Symbolic Search for Knowledge Graph Complex Query Answering
While neuro-symbolic search utilized neural link predictions achieve superior accuracy, they encounter significant complexity bottlenecks: (i) Data complexity typically scales quadratically with the number of entities in the knowledge graph, and (ii) Query complexity becomes NP-hard for cyclic queries.
A Practical Introduction to Deep Reinforcement Learning
Deep reinforcement learning (DRL) has emerged as a powerful framework for solving sequential decision-making problems, achieving remarkable success in a wide range of applications, including game AI, autonomous driving, biomedicine, and large language models.
MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning
Multimodal Federated Learning (MFL) is a distributed approach that enhances the efficiency and quality of multimodal learning, ensuring collaborative work and privacy protection.
Riemannian Denoising Diffusion Probabilistic Models
We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets of functions, including most of the manifolds relevant to applications.
Tempo: Application-aware LLM Serving with Mixed SLO Requirements
The integration of Large Language Models (LLMs) into diverse applications, ranging from interactive chatbots and cloud AIOps to intelligent agents, has introduced a wide spectrum of Service Level Objectives (SLOs) for responsiveness.
Joint Topology and Power Optimization for Multi-UAV Collaborative Secure Communication
Subsequently, the non-convex constraints are converted into convex terms, and a double-loop search algorithm is proposed to solve the transmit power minimization problem.
The PHD/CPHD filter for Multiple Extended Target Tracking with Trajectory Set Theory and Explicit Shape Estimation
These two methods are deduced from the famous Probability Hypothesis Density (PHD) filter and the Cardinality-PHD (CPHD) filter, respectively.
Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions
Despite substantial progress, open challenges remain in preserving emergent reasoning and linguistic diversity, enabling efficient adaptation to continually evolving teacher models and datasets, and establishing comprehensive evaluation protocols.
SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training
For example, on the Llama 70B model, compared to state-of-the-art methods, SlimPipe significantly boosts the Model FLOPs Utilization (MFU) to up to $1. 57\times$ for a context length of 512K.
EarthGPT-X: Enabling MLLMs to Flexibly and Comprehensively Understand Multi-Source Remote Sensing Imagery
Recent advances in the visual-language area have developed natural multi-modal large language models (MLLMs) for spatial reasoning through visual prompting.
Dynamic Compressing Prompts for Efficient Inference of Large Language Models
We model prompt compression as a Markov Decision Process (MDP), enabling the DCP-Agent to sequentially remove redundant tokens by adapting to dynamic contexts and retaining crucial content.
PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025.
CliniChat: A Multi-Source Knowledge-Driven Framework for Clinical Interview Dialogue Reconstruction and Evaluation
So we propose CliniChat, a framework that integrates multi-source knowledge to enable LLMs to simulate real-world clinical interviews.
BioChemInsight: An Open-Source Toolkit for Automated Identification and Recognition of Optical Chemical Structures and Activity Data in Scientific Publications
Automated extraction of chemical structures and their bioactivity data is crucial for accelerating drug discovery and enabling data-driven pharmaceutical research.
The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation
Motion expression video segmentation is designed to segment objects in accordance with the input motion expressions.
Inference Optimization
Referring Video Object Segmentation
+4
GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill
Extensive experiments across diverse embodiments and learning paradigms demonstrate GROVE's effectiveness, achieving 22. 2% higher motion naturalness and 25. 7% better task completion scores while training 8. 4x faster than previous methods.
Dexterous Manipulation through Imitation Learning: A Survey
Dexterous manipulation, which refers to the ability of a robotic hand or multi-fingered end-effector to skillfully control, reorient, and manipulate objects through precise, coordinated finger movements and adaptive force modulation, enables complex interactions similar to human hand dexterity.
Gaussian Process Tilted Nonparametric Density Estimation using Fisher Divergence Score Matching
We present three Fisher divergence (FD) minimization algorithms for learning Gaussian process (GP) based score models for lower dimensional density estimation problems.
Reconfigurable Codebook-Based Beamforming for RDARS-Aided mmWave MU-MIMO Systems
In RDARS-aided mmWave systems, the active and passive beamforming design and working mode configuration for reconfigurable elements are crucial for system performance.
Decoding Covert Speech from EEG Using a Functional Areas Spatio-Temporal Transformer
Covert speech involves imagining speaking without audible sound or any movements.
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation.
Hierarchical Attention Networks for Lossless Point Cloud Attribute Compression
In this paper, we propose a deep hierarchical attention context model for lossless attribute compression of point clouds, leveraging a multi-resolution spatial structure and residual learning.
Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions
This study systematically analyzes geopolitical bias across 11 prominent Large Language Models (LLMs) by examining their responses to seven critical topics in U. S.-China relations.
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding.
Center-guided Classifier for Semantic Segmentation of Remote Sensing Images
i. e., larger intraclass variance, which makes semantic segmentation for remote sensing images more challenging.
PAPI-Reg: Patch-to-Pixel Solution for Efficient Cross-Modal Registration between LiDAR Point Cloud and Camera Image
To address this issue, we propose a framework that projects point clouds into several 2D representations for matching with camera images, which not only leverages the geometric characteristic of LiDAR point clouds more effectively but also bridge the domain gap between the point cloud and image.
StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion
Existing methods encounter a fundamental dilemma in learning humanoid locomotion: reinforcement learning with handcrafted rewards can achieve agile locomotion but produces unnatural gaits, while Generative Adversarial Imitation Learning (GAIL) with motion capture data yields natural movements but suffers from unstable training processes and restricted agility.
Fuzzy Rule-based Differentiable Representation Learning
Subsequently, a novel differentiable optimization method is proposed for the consequence part learning which can preserve the model's interpretability and transparency while further exploring the nonlinear relationships within the data.
Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach
With the rapid advancement of Artificial Intelligence (AI), Large Language Models (LLMs) have significantly impacted a wide array of domains, including healthcare, engineering, science, education, and mathematical reasoning.
Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment.
We Care Each Pixel: Calibrating on Medical Segmentation Model
Medical image segmentation is fundamental for computer-aided diagnostics, providing accurate delineation of anatomical structures and pathological regions.
DDCSR: A Novel End-to-End Deep Learning Framework for Cortical Surface Reconstruction from Diffusion MRI
Diffusion MRI (dMRI) plays a crucial role in studying brain white matter connectivity.
FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion
3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling real-time positioning and the construction of high-fidelity maps.
EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting
We first establish a unified feature distribution in the translator's image encoder through self-supervised learning on a large-scale dataset, enabling photos of any style to be embedded into a unified feature representation.
CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models
To address these limitations, we introduce a holistic code critique benchmark for LLMs called CodeCriticBench.
Coherency Improved Explainable Recommendation via Large Language Model
Explainable recommender systems are designed to elucidate the explanation behind each recommendation, enabling users to comprehend the underlying logic.
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning.
3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments
The field of visual localization has been researched for several decades and has meanwhile found many practical applications.
SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models
The increasing application of multi-modal large language models (MLLMs) across various sectors have spotlighted the essence of their output reliability and accuracy, particularly their ability to produce content grounded in factual information (e. g. common and domain-specific knowledge).
Continuous-Aperture Array Based OAM High-Capacity Communication For Metaverse
The extensive data interaction demands of an immersive metaverse necessitate the adoption of emerging technologies to enable high-capacity communication.
Collaborative Filtering Meets Spectrum Shift: Connecting User-Item Interaction with Graph-Structured Side Information
However, when graph-structured side information (e. g., multimodal similarity graphs or social networks) is integrated into the U-I bipartite graph, existing graph collaborative filtering methods fall short of achieving satisfactory performance.
NatureLM: Deciphering the Language of Nature for Scientific Discovery
Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages.
Multi-Agent Collaboration for Multilingual Code Instruction Tuning
Recent advancement in code understanding and generation demonstrates that code LLMs fine-tuned on a high-quality instruction dataset can gain powerful capabilities to address wide-ranging code-related tasks.
HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion
Graph is the more flexible structure, however, there are two major challenges when modeling spatial-spectral properties with graph: \emph{1) constructing the customized graph structure for spatial-spectral relationship priors}; \emph{2) learning the unified spatial-spectral representation through the graph}.
DobLIX: A Dual-Objective Learned Index for Log-Structured Merge Trees
In this paper, we introduce DobLIX, a dual-objective learned index specifically designed for Log-Structured Merge(LSM) tree-based key-value stores.
FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
Text-driven video generation has advanced significantly due to developments in diffusion models.
Middleman Bias in Advertising: Aligning Relevance of Keyphrase Recommendations with Search
E-commerce sellers are recommended keyphrases based on their inventory on which they advertise to increase buyer engagement (clicks/sales).
Advancing Generative Artificial Intelligence and Large Language Models for Demand Side Management with Internet of Electric Vehicles
This paper explores the integration of LLMs into energy management, emphasizing their roles in automating the optimization of DSM strategies with Internet of electric vehicles.
CD-Lamba: Boosting Remote Sensing Change Detection via a Cross-Temporal Locally Adaptive State Space Model
However, existing remote sensing change detection (RSCD) approaches based on Mamba frequently struggle to effectively perceive the inherent locality of change regions as they direct flatten and scan RS images (i. e., the features of the same region of changes are not distributed continuously within the sequence but are mixed with features from other regions throughout the sequence).
SpikSSD: Better Extraction and Fusion for Object Detection with Spiking Neuron Networks
However, efficiently conducting feature extraction and fusion under the spiking characteristics of SNNs for object detection remains a pressing challenge.
A Novel Scene Coupling Semantic Mask Network for Remote Sensing Image Segmentation
To deal with such limitations, this paper proposes a novel scene-Coupling semantic mask network, which reconstructs the vanilla attention with scene coupling and local global semantic masks strategies.
Large Language Models for Bioinformatics
With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications.
GiNet: Integrating Sequential and Context-Aware Learning for Battery Capacity Prediction
The surging demand for batteries requires advanced battery management systems, where battery capacity modelling is a key functionality.
LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
By reconceptualizing the update task as an end-to-end map generation process grounded in historical map data, we introduce a paradigm shift in map updating that simultaneously generates vectorized maps and change information.
Balanced Multi-view Clustering
The widely used joint training paradigm in MvC is potentially not fully leverage the multi-view information, since the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views.
Digital-Analog Transmission based Emergency Semantic Communications
For EWC scene, we propose a performance-constrained semantic coding model, which considers the effects of the semantic noise and the channel noise.
Unleashing Correlation and Continuity for Hyperspectral Reconstruction from RGB Images
Therefore, we fully explore these inter-spectral relationships and propose a Correlation and Continuity Network (CCNet) for HSI reconstruction from RGB images.
Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition
Recently, end-to-end automatic speech recognition has become the mainstream approach in both industry and academia.
Decoupled Motion Expression Video Segmentation
In this work, we propose DMVS, a simple framework constructed on the existing query-based VIS model, emphasizing decoupling the task into video instance segmentation and motion expression understanding.
Instance Segmentation
Referring Video Object Segmentation
+5
Less Attention is More: Prompt Transformer for Generalized Category Discovery
This results in a model with more yet scattered attention, where neither excessive nor insufficient focus can grasp subtle differences to classify fine-grained unknown and known categories.
STeInFormer: Spatial-Temporal Interaction Transformer Architecture for Remote Sensing Change Detection
To address this problem, we present STeInFormer, a spatial-temporal interaction Transformer architecture for multi-temporal feature extraction, which is the first general backbone network specifically designed for RSCD.
Mathematics and Machine Creativity: A Survey on Bridging Mathematics with AI
This paper presents a comprehensive overview on the applications of artificial intelligence (AI) in mathematical research, highlighting the transformative role AI has begun to play in this domain.
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks yet still are vulnerable to external threats, particularly LLM Denial-of-Service (LLM-DoS) attacks.
SpatialMe: Stereo Video Conversion Using Depth-Warping and Blend-Inpainting
Stereo video conversion aims to transform monocular videos into immersive stereo format.
Learning Implicit Features with Flow Infused Attention for Realistic Virtual Try-On
Image-based virtual try-on is challenging since the generated image should fit the garment to model images in various poses and keep the characteristics and details of the garment simultaneously.
High-speed and High-quality Vision Reconstruction of Spike Camera with Spike Stability Theorem
To realize high-speed and high-quality vision reconstruction of the spike camera, we propose a new spike stability theorem that reveals the relationship between spike stream characteristics and stable light intensity.
STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation
In order to combine the two distinct types of information, some additional challenges are encountered: 1) Modality erasure: Vanilla graph convolution, which proves rather useful in collaborative filtering, however erases multimodal information; 2) Modality forgetting: Multimodal information tends to be gradually forgotten as the recommendation loss essentially facilitates the learning of collaborative information.
Explainable Fuzzy Neural Network with Multi-Fidelity Reinforcement Learning for Micro-Architecture Design Space Exploration
With the continuous advancement of processors, modern micro-architecture designs have become increasingly complex.
Predicting Human Brain States with Transformer
The human brain is a complex and highly dynamic system, and our current knowledge of its functional mechanism is still very limited.
Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset
Object detection in event streams has emerged as a cutting-edge research area, demonstrating superior performance in low-light conditions, scenarios with motion blur, and rapid movements.
ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance
In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token prediction formulation.
Ranked #140 on
Visual Question Answering
on MM-Vet
Rate-Distortion Optimized Skip Coding of Region Adaptive Hierarchical Transform Coefficients for MPEG G-PCC
To address this problem, we propose an adaptive skip coding method for RAHT, which adaptively determines whether to encode the residuals of the last several layers or not, thereby improving the coding efficiency.
LAA-Net: A Physical-prior-knowledge Based Network for Robust Nighttime Depth Estimation
Existing self-supervised monocular depth estimation (MDE) models attempt to improve nighttime performance by using GANs to transfer nighttime images into their daytime versions.
Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-Manipulator
Specifically, we focus on the problem of how to coordinate the floating base and the robotic arm of a wheeled-quadrupedal manipulator robot to achieve direct six-dimensional (6D) end-effector (EE) pose tracking in task space.
CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels
However, the scarcity of high-quality long-context summarization datasets has hindered further advancements in this area.
CAdam: Confidence-Based Optimization for Online Learning
Modern recommendation systems frequently employ online learning to dynamically update their models with freshly collected data.
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input.
Generative Fuzzy System for Sequence Generation
In this work, we introduce the fuzzy system, a classical modeling method that combines data and knowledge-driven mechanisms, to generative tasks.
Exploring Feature-based Knowledge Distillation for Recommender System: A Frequency Perspective
By defining knowledge as different frequency components of the features, we theoretically demonstrate that regular feature-based knowledge distillation is equivalent to equally minimizing losses on all knowledge and further analyze how this equal loss weight allocation method leads to important knowledge being overlooked.
Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios
Artificial Intelligence (AI) has become essential in modern healthcare, with large language models (LLMs) offering promising advances in clinical decision-making.
Counterfactual Learning-Driven Representation Disentanglement for Search-Enhanced Recommendation
To address this, we propose a Counterfactual learning-driven representation disentanglement framework for search-enhanced recommendation, based on the common belief that a user would click an item under a query not solely because of the item-query match but also due to the item's query-independent general features (e. g., color or style) that interest the user.
CDXLSTM: Boosting Remote Sensing Change Detection with Extended Long Short-Term Memory
In complex scenes and varied conditions, effectively integrating spatial-temporal context is crucial for accurately identifying changes.
LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios
As Large Language Models (LLMs) evolve in natural language processing (NLP), their ability to stably follow instructions in long-context inputs has become critical for real-world applications.
MdEval: Massively Multilingual Code Debugging
Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet.
E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large language models.
Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
Instruction-following capabilities in LLMs have progressed significantly, enabling more complex user interactions through detailed prompts.
Integration of Communication and Computational Imaging
Herein, we propose a novel framework that integrates communication and computational imaging (ICCI) to break through the inherent isolation between communication and computational imaging for remote perception.
CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
It leverages supervised contrastive learning (SCL) and k-nearest neighbours (KNN) to construct and calibrate raw probability density estimates, and implements a refitting procedure to resume end-to-end discriminative models ready to produce final estimates for large-scale imaging data.
Brain-like Functional Organization within Large Language Models
In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs), the foundational organizational structure of the human brain.
Calibrating Deep Neural Network using Euclidean Distance
This research introduces a novel loss function called Focal Calibration Loss (FCL), designed to improve probability calibration while retaining the advantages of Focal Loss in handling difficult samples.
Analyzing Nobel Prize Literature with Large Language Models
This study examines the capabilities of advanced Large Language Models (LLMs), particularly the o1 model, in the context of literary analysis.
Corrected Soft Actor Critic for Continuous Control
The Soft Actor-Critic (SAC) algorithm is known for its stability and high sample efficiency in deep reinforcement learning.
MAC Revivo: Artificial Intelligence Paves the Way
The vast adoption of Wi-Fi and/or Bluetooth capabilities in Internet of Things (IoT) devices, along with the rapid growth of deployed smart devices, has caused significant interference and congestion in the industrial, scientific, and medical (ISM) bands.
Real-time Stereo-based 3D Object Detection for Streaming Perception
StreamDSGN is an end-to-end framework that directly predicts the 3D properties of objects in the next moment by leveraging historical information, thereby alleviating the accuracy degradation of streaming perception.
AoI-Aware Resource Allocation for Smart Multi-QoS Provisioning
To address these challenges, we propose a DRL-based framework for AoI-aware optimal resource allocation in mURLLC-driven multi-QoS schemes, leveraging AoI as a core metric within the finite blocklength regime.
FBC-Enhanced ε-Effective Capacity Optimization for NOMA
The advent of massive ultra-reliable and low-latency communications (mURLLC) has introduced a critical class of time- and reliability-sensitive services within next-generation wireless networks.
The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations.
ERCache: An Efficient and Reliable Caching Framework for Large-Scale User Representations in Meta's Ads System
The increasing complexity of deep learning models used for calculating user representations presents significant challenges, particularly with limited computational resources and strict service-level agreements (SLAs).
As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
The experimental results show that BNF achieves comparable performance to the best methods on QA benchmarks, while its performance decrease on the four reasoning benchmarks is significantly lower compared to the best methods, thus striking a better balance between value alignment and reasoning ability.
EEG Emotion Copilot: Optimizing Lightweight LLMs for Emotional EEG Interpretation with Assisted Medical Record Generation
This paper presents the EEG Emotion Copilot, a system optimizing a lightweight large language model (LLM) with 0. 5B parameters operating in a local setting, which first recognizes emotional states directly from EEG signals, subsequently generates personalized diagnostic and treatment suggestions, and finally supports the automation of assisted electronic medical records.
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
The X-Prompt framework first pre-trains a video object segmentation foundation model using RGB data, and then utilize the additional modality of the prompt to adapt it to downstream multi-modal tasks with limited data.
Multi-Atlas Brain Network Classification through Consistency Distillation and Complementary Information Fusion
Some recent methods have proposed utilizing multiple atlases, but they neglect consistency across atlases and lack ROI-level information exchange.
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
-Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis.
General Compression Framework for Efficient Transformer Object Tracking
Thus, we propose a general model compression framework for efficient transformer object tracking, named CompressTracker, to reduce the size of a pre-trained tracking model into a lightweight tracker with minimal performance degradation.
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models.
Dataset Distillation-based Hybrid Federated Learning on Non-IID Data
In federated learning, the heterogeneity of client data has a great impact on the performance of model training.
Performance Boundary Analyses for Statistical Multi-QoS Framework Over 6G SAGINs
In response to the complex, heterogeneous, and dynamic serving scenarios and stringent performance expectations for 6G SAGINs, it is crucial to undertake modeling, assurance, and analysis of the key technologies, aligned with the diverse demands for QoS provisioning in the non-asymptotic regime, i. e., when implementing finite blocklength coding (FBC) as a new dimension for error-rate bounded QoS metric.
The Roles of Generative Artificial Intelligence in Internet of Electric Vehicles
With the advancements of generative artificial intelligence (GenAI) models, their capabilities are expanding significantly beyond content generation and the models are increasingly being used across diverse applications.
ManiNeg: Manifestation-guided Multimodal Pretraining for Mammography Classification
Breast cancer is a significant threat to human health.
Reinforcement Leaning for Infinite-Dimensional Systems
We then develop a moment kernel transform to map the parameterized system and the value function of an RL problem into a reproducing kernel Hilbert space.
AIM 2024 Challenge on Video Saliency Prediction: Methods and Results
The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences.
FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model
In the facial animation transfer component, we propose a novel Expression-driven Multi-avatar Animator, which first maps expressive semantics to the facial control parameters of 3D avatars and then imposes perceptual constraints between the input and output images to maintain expression consistency.
Atmospheric Turbulence-Immune Free Space Optical Communication System based on Discrete-Time Analog Transmission
To effectively mitigate the influence of atmospheric turbulence, a novel discrete-time analog transmission free-space optical (DTAT-FSO) communication scheme is proposed.
IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web
We have conducted extensive experiments on existing large multimodal models, offering insights into their performance and areas for improvement in image-to-web domain.
Matrix Profile for Anomaly Detection on Multidimensional Time Series
This paper delves into the problem of anomaly detection in multidimensional time series, a common occurrence in real-world applications.
Bayesian Dynamic Factor Models for High-dimensional Matrix-valued Time Series
To determine the dimension of the factor matrix, we employ an importance-sampling estimator based on the cross-entropy method to estimate marginal likelihoods.
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
In the realm of Large Language Models (LLMs), the ability to process long contexts is increasingly crucial for tasks such as multi-round dialogues, code generation, and document summarization.
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes.
Preserving Individuality while Following the Crowd: Understanding the Role of User Taste and Crowd Wisdom in Online Product Rating Prediction
Our findings underscore the significance of individual user tastes in the context of online product rating prediction and the robustness of our approach across different model architectures.
Cycle Pixel Difference Network for Crisp Edge Detection
We construct a U-shape encoder-decoder model named CPD-Net that successfully addresses these two issues simultaneously.
Interpreting and Improving Large Language Models in Arithmetic Calculation
In this work, we delve into uncovering a specific mechanism by which LLMs execute calculations.
MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning
In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data.
Are LLM-based Recommenders Already the Best? Simple Scaled Cross-entropy Unleashes the Potential of Traditional Sequential Recommenders
Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve `state-of-the-art' performance in sequential recommendation.
When Diffusion MRI Meets Diffusion Model: A Novel Deep Generative Model for Diffusion MRI Generation
This achievement underscores a substantial progression in enhancing dMRI quality, highlighting the potential of our novel generative approach to revolutionize dMRI imaging standards.
Coarse-to-Fine Detection of Multiple Seams for Robotic Welding
The RGB image is used to obtain the region of interest by approximately localizing the weld seams, and the point cloud is used to achieve the fine-edge extraction of the weld seams within the region of interest using region growth.
UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track
Referring video object segmentation (RVOS) relies on natural language expressions to segment target objects in video.
Referring Video Object Segmentation
Semantic Segmentation
+1
Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame.
Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting
In response, we propose ProRBP, a novel Progressive Retrieved Behavior-augmented Prompting framework for integrating search scenario-oriented knowledge with LLMs effectively.
A Systematic Evaluation of Generated Time Series and Their Effects in Self-Supervised Pretraining
Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks.
Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content.
Breaking Limits of Line-of-Sight MIMO Capacity in 6G Wireless Communications
Multiple-input-multiple-output (MIMO) has been proved its success for the fourth generation (4G) long term evolution (LTE) and is one of the key technical enablers for evolved mobile broadband (eMBB) in the fifth generation (5G) wireless communications.
Achieving Practical OAM Based Wireless Communications With Misaligned Transceiver
To maintain the orthogonality among different OAM modes at the receiver, the strict alignment between transmit and receive antennas is highly demanded.
Quasi-Fractal UCA Based OAM for Highly Efficient Orthogonal Transmission
We perform the two-dimension OAM modulation (TOM) and demodulation (TOD) schemes with the orthogonal OAM mode number exceeding the array-element number, which is beyond the traditional concept of multiple antennas based wireless communications.
Enhanced Traffic Flow Prediction with Multi-Segment Fusion Tensor Graph Convolutional Networks
Accurate traffic Flow Prediction can assist in traffic management, route planning, and congestion mitigation, which holds significant importance in enhancing the efficiency and reliability of intelligent transportation systems (ITS).
UpLIF: An Updatable Self-Tuning Learned Index Framework
The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search efficiency and index size reduction; however, a significant challenge inherent in learned index modeling is its constrained support for update operations, necessitated by the requirement for a fixed distribution of records.
Integrating Controllable Motion Skills from Demonstrations
The expanding applications of legged robots require their mastery of versatile motion skills.
DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecasting
Our proposed model, named DRFormer, is evaluated on various real-world datasets, and experimental results demonstrate its superiority compared to existing methods.
Rate Maximization for RIS-Assisted OAM Multiuser Wireless Communications
Conventional multiple-input multiple-out (MIMO) technologies have encountered bottlenecks of significantly increasing spectrum efficiencies of wireless communications due to the low degrees of freedom in practical line-of-sight scenarios and severe path loss of high frequency carriers.
A new approach for encoding code and assisting code understanding
Some companies(e. g., Microsoft Research and Google DeepMind) have discovered some of the limitations of GPTs autoregressive paradigm next-word prediction, manifested in the model lack of planning, working memory, backtracking, and reasoning skills.
STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data
In this study, we propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating CNN and RNN to capture both temporal and spatial features of brain activity.
Exploring Loss Landscapes through the Lens of Spin Glass Theory
Specifically, we used (1) random walk in the parameter space of DNNs to unravel the structures in their loss landscape; (2) a permutation-interpolation protocol to study the connection between copies of identical regions in the loss landscape due to the permutation symmetry in the hidden layers; (3) hierarchical clustering to reveal the hierarchy among trained solutions of DNNs, reminiscent of the so-called Replica Symmetry Breaking (RSB) phenomenon (i. e. the Parisi solution) in spin glass; (4) finally, we examine the relationship between the ruggedness of DNN's loss landscape and its generalizability, showing an improvement of flattened minima.
MetaHive: A Cache-Optimized Metadata Management for Heterogeneous Key-Value Stores
KV stores frequently consist of heterogeneous clusters, characterized by varying hardware specifications of the deployment nodes, with each node potentially running a distinct version of the KV store software.
Channel Estimation for Movable-Antenna MIMO Systems Via Tensor Decomposition
In this letter, we investigate the channel estimation problem for MIMO wireless communication systems with movable antennas (MAs) at both the transmitter (Tx) and receiver (Rx).
Virtual Full-Duplex Wireless Communications with Zero-Interval Modulation and Sampling
In ZIMS-VFD, the transceiver inserts a zero-interval for each symbol in the transmit signal and provides self-interference (SI)-free intervals for itself.
Resource Allocation for 5G-UAV Based Emergency Wireless Communications
Numerical results show that the new heterogeneous Fisher-Snedecor $\mathcal{F}$ composite fading channel adapted resource allocation schemes can achieve higher capacity and energy efficiency than those of traditional channel model adapted resource allocation schemes, thus providing better communications service for post-disaster areas.
Affective Behaviour Analysis via Progressive Learning
To advance this, the 7th Affective Behavior Analysis in-the-wild (ABAW) competition establishes two tracks: i. e., the Multi-task Learning (MTL) Challenge and the Compound Expression (CE) challenge based on Aff-Wild2 and C-EXPR-DB datasets.
Enhancing LLM's Cognition via Structurization
Besides, we show the feasibility of distilling advanced LLMs' language processing abilities to a smaller yet effective StruXGPT-7B to execute structurization, addressing the practicality of our approach.
Norface: Improving Facial Expression Analysis by Identity Normalization
First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background.
Ranked #1 on
Facial Expression Recognition (FER)
on DISFA
Robust Multi-Beam Secure mmWave Wireless Communication for Hybrid Wiretapping Systems
In this paper, we consider the physical layer (PHY) security problem for hybrid wiretapping wireless systems in millimeter wave transmission, where active eavesdroppers (AEs) and passive eavesdroppers (PEs) coexist to intercept the confidential messages and emit jamming signals.
Joint Information and Jamming Beamforming for Securing IoT Networks With Rate-Splitting
The goal of this paper is to address the physical layer (PHY) security problem for multi-user multi-input single-output (MU-MISO) Internet of Things (IoT) systems in the presence of passive eavesdroppers (Eves).
Mode Hopping with OAM-Based Index Modulation
In this paper, we propose an MH with OAM-based index modulation scheme, where several OAM-modes are activated for hopping, to achieve high SE at a given bit error rate in radio vortex wireless communications.
Mode Hopping for Anti-Jamming in Radio Vortex Wireless Communications
In particular, we propose the mode hopping (MH) scheme for antijamming within the narrow frequency band.
Joint OAM Multiplexing and OFDM in Sparse Multipath Environments
In this paper, a hybrid orthogonal division multiplexing (HODM) scheme by using OAM multiplexing and orthogonal frequency division multiplexing (OFDM) in conjunction is proposed to achieve high-capacity wireless communications in sparse multipath environments, where the scatterers are sparse.
Decomposed and Distributed Directional Modulation for Secure Wireless Communication
This paper presents an AN-aided decomposed and distributed directional modulation (D3M) scheme for secure wireless communications, which takes advantage of the spatial signatures to achieve an extra range-dimension security apart from the angles.
EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing
Specifically, a shared visual encoding method is developed to establish the spatial pattern interpretation relationships between the multi-scale representations of input images and various visual prompts.
JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation
However, this paradigm distills view-agnostic 2D image distributions into the rendering distribution of 3D representation for each view independently, overlooking the coherence across views and yielding 3D inconsistency in generations.
Index Modulation Embedded Mode Hopping for Anti-Jamming
To achieve efficient anti-jamming and increase SE of wireless communications with slight computational complexity cost, in this paper we propose an index-modulation embedded mode-hopping (IM-MH) scheme, which simultaneously activates several OAM-modes for hopping along with additional index information and signal information transmission.
RIS-Based Self-Interference Cancellation for Full-Duplex Broadband Transmission
The problem is solved with alternate optimization (AO) algorithm in three cases: ideal case, where both the amplitude and phase of each RIS unit cell can be controlled independently and continuously, continuous phases, where the phase of each RIS unit cell can be controlled independently, while the amplitude is fixed to one, and discrete phases, where the RC of each RIS unit cell can only take discrete values and these discrete values are equally spaced on the unit circle.
Generative AI Driven Task-Oriented Adaptive Semantic Communications
The existing TOSC frameworks focus on extracting the full semantic features of source data and learning low-dimensional channel inputs to transmit them within limited bandwidth resources.
Phases Calibration of RIS Using Backpropagation Algorithm
Reconfigurable intelligent surface (RIS) technology has emerged in recent years as a promising solution to the ever-increasing demand for wireless communication capacity.
Reconfigurable-Intelligent-Surface Assisted Orbital-Angular-Momentum Secure Communications
As a kind of wavefront with helical phase, orbital angular momentum (OAM) shows the great potential to enhance the security results of wireless communications due to its unique orthogonality and central hollow electromagnetic wave structure.
Scalable Extraction Based Semantic Communication for 6G Wireless Networks
In this article, we introduce a novel Scalable Extraction based Semantic Communication (SE-SC) model to support the potential applications in 6G wireless networks and then analyze its feasibility.
Digital-Analog Transmission Framework for Task-Oriented Semantic Communications
The semantic feature, constituted by analog vectors of a lower dimensionality relative to the original source data, reserves the meaning of the source data.
HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities.
Enhanced Battery Degradation-Aware Scheduling for Distribution Network with Electric Vehicle Load
We formulate a multi-objective framework for optimizing battery scheduling with the goals of minimizing monetary costs and improving network performance.
Evolutionary Morphology Towards Overconstrained Locomotion via Large-Scale, Multi-Terrain Deep Reinforcement Learning
Then, we implemented a large-scale, multi-terrain deep reinforcement learning framework to train these reconfigurable limbs for a comparative analysis of overconstrained locomotion in energy efficiency.
Stochastic Solutions for Simultaneous Seismic Data Denoising and Reconstruction via Score-based Generative Models
We also analyze the advantages of our approach and concluded that successful generative modeling of seismic data by the score-based generative models (SGMs) is the key to posterior sampling for the inverse problems, which all benefit from the seismic data prior implicit in the trained score network in the SGMs.
Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition
In this paper, we propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++.
Assessing "Implicit" Retrieval Robustness of Large Language Models
Our findings reveal that fine-tuning on a mix of gold and distracting context significantly enhances the model's robustness to retrieval inaccuracies, while still maintaining its ability to extract correct answers when retrieval is accurate.
D2LLM: Decomposed and Distilled Large Language Models for Semantic Search
In this paper, we present D2LLMs-Decomposed and Distilled LLMs for semantic search-that combines the best of both worlds.
LOGCAN++: Adaptive Local-global class-aware network for semantic segmentation of remote sensing imagery
In particular, we introduce affine transformations in the LCA module for adaptive extraction of local class representations to effectively tolerate scale and orientation variations in remotely sensed images.
Ranked #10 on
Semantic Segmentation
on LoveDA
Rethinking Remote Sensing Change Detection With A Mask View
Consequently, we further propose the instance network CDMaskFormer customized for the change detection task, which includes: (i) a Spatial-temporal convolutional attention-based instantiated change extractor to capture spatio-temporal context simultaneously with lightweight operations; and (ii) a scene-guided axial attention-instantiated transformer decoder to extract more spatial details.
Ranked #3 on
Change Detection
on DSIFN-CD
DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation
This paper overcomes these limitations and presents an industrial-grade solution named DuMapNet that outputs standardized, vectorized map elements and their topology in an end-to-end paradigm.
DDLNet: Boosting Remote Sensing Change Detection with Dual-Domain Learning
Remote sensing change detection (RSCD) aims to identify the changes of interest in a region by analyzing multi-temporal remote sensing images, and has an outstanding value for local development monitoring.
Ranked #19 on
Change Detection
on WHU-CD
Estimating Difficulty Levels of Programming Problems with Pre-trained Model
As the demand for programming skills grows across industries and academia, students often turn to Programming Online Judge (POJ) platforms for coding practice and competition.
Integrated Sensing and Communication for Anti-Jamming with OAM
The spectrum share and open nature of wireless channels enable integrated sensing and communication (ISAC) susceptible to hostile jamming attacks.
Double-RIS-Assisted Orbital Angular Momentum Near-Field Secure Communications
To satisfy the various demands of growing devices and services, emerging high-frequency-based technologies promote near-field wireless communications.
Achieving High Capacity Transmission With N-Dimensional Quasi-Fractal UCA
Then, we investigate different dimensional multiplexing transmission schemes based on the corresponding QF-UCA antenna structure with various array-element layouts and evaluate the optimal layout type and dimension to obtain the highest channel capacity with a fixed number of array-elements.
Learning to utilize image second-order derivative information for crisp edge detection
In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for crisp edge detection.
Fractal OAM Generation and Detection Schemes
In this paper, we propose Talbot-effect-based fractal OAM generation and detection schemes using a uniform circular array (UCA) to significantly improve capacity and BER performance in unaligned OAM transmissions.
Modeling and Performance Analysis of OAM-NFC Systems
In this paper, we model and analyze the performance of the orbital angular momentum based NFC (OAM-NFC) system, which can significantly increase the capacity of NFC.
Activation Map-based Vector Quantization for 360-degree Image Semantic Communication
In virtual reality (VR) applications, 360-degree images play a pivotal role in crafting immersive experiences and offering panoramic views, thus improving user Quality of Experience (QoE).
Statistical QoS Provisioning Architecture for 6G Satellite-Terrestrial Integrated Networks
To effectively measure data freshness in satellite-terrestrial integrated communications, age of information (AoI) has recently surfaced as a new dimension of QoS metric to support time-sensitive applications.
Leveraging Pedagogical Theories to Understand Student Learning Process with Graph-based Reasonable Knowledge Tracing
The advancement of deep learning in this field has led to deep-learning knowledge tracing (DLKT) models that prioritize high predictive accuracy.
Nutrition Estimation for Dietary Management: A Transformer Approach with Depth Sensing
In this paper, we propose NuNet, a transformer-based network designed for nutrition estimation that utilizes both RGB and depth information from food images.
LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising
Event camera has significant advantages in capturing dynamic scene information while being prone to noise interference, particularly in challenging conditions like low threshold and low illumination.
