Page 5 - Paper Library - AiPaper

Exploring Perception-Based Techniques for Redirected Walking in VR: A Comprehensive Survey

Published:5/22/2025

Perception-Based Redirected Walking TechniquesUser Experience in Virtual RealityExploration of Virtual EnvironmentsClassification of RDW AlgorithmsSurvey of Virtual Reality Techniques

This paper surveys perceptionbased redirected walking techniques in VR, reviewing 232 papers and analyzing 165. It introduces a new taxonomy categorizing RDW algorithms into Gains, Gain Application, Target Orientation Calculation, and Enhancements, emphasizing the importance of

Redirected Walking for Exploring Immersive Virtual Spaces With HMD: A Comprehensive Review and Recent Advances

Published:5/31/2022

Redirected Walking TechniquesExploration of Immersive Virtual SpacesVirtual-Physical Movement MappingRedirection Controller MethodsUser Movement Adjustment Strategies

This paper reviews Redirected Walking (RDW) techniques, addressing how to achieve immersive virtual experiences within limited physical space. It categorizes redirection manipulations, discusses controller methods, and incorporates emerging technologies like deep learning, summar

Predictive multiuser redirected walking using artificial potential fields

Published:8/8/2024

Multi-User Redirected WalkingArtificial Potential FieldsPredictive Redirected Walking SystemsClothoid Trajectory GenerationUser Experience in Virtual Environments

This paper introduces two novel predictive redirected walking systems using clothoidbased algorithms, effectively addressing multiuser navigation in limited physical spaces, and demonstrating improved user experience over traditional reactive methods.

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Published:6/10/2025

Vision-Language-Action Model3D Manipulation LearningInput-Output Alignment2D Heatmap PredictionSample Efficiency Improvement

BridgeVLA introduces a novel visionlanguageaction model for 3D manipulation, addressing inefficiencies in existing models. By projecting 3D data to 2D images and using heatmaps for action prediction, it achieves stateoftheart performance on various benchmarks.

Prompting Science Report 4: Playing Pretend: Expert Personas Don't Improve Factual Accuracy

Published:1/1/2025

Impact of Expert Personas on Model PerformancePerformance Evaluation on Multiple-Choice QuestionsComparison of Domain-Specific and Low-Knowledge PersonasGPQA Diamond and MMLU-Pro BenchmarkingRelation between AI Model Performance and Persona Prompts

The study investigates whether assigning expert personas to large language models improves performance on difficult objective questions. Findings reveal no significant accuracy gains from expert personas, while mismatched and lowknowledge personas often degrade model performance

Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System

Published:4/17/2024

LLM-based Recommendation SystemsCollaborative Filtering Recommender SystemsCold-Start Recommendation OptimizationCross-Domain Recommendation SystemUser/Item Embedding Generation

The ALLMRec system combines collaborative knowledge with large language models to excel in both cold and warm start scenarios, enhancing user experience while being modelagnostic and efficient.

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

Published:10/17/2023

4D Gaussian Splatting RepresentationDynamic Scene ReconstructionReal-Time RenderingSpatiotemporal ModelingMultiview Scene Synthesis

This paper introduces a 4D Gaussian Splatting method for dynamic scene reconstruction and rendering, addressing the challenge of generating highquality 3D scenes from 2D images. By viewing spacetime as a whole, it models geometry and dynamic appearance efficiently, outperforming

ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation

Published:12/3/2025

Camera-Controlled Trajectory Video Generation3D Geometric GuidanceMonocular Video Multi-Trajectory SupervisionParaDrive DatasetTwo-Stage Training Paradigm

This paper presents ReCamDriving, a visionbased framework for generating videos from novel trajectories using camera control. By leveraging dense 3D Gaussian Splatting as geometric guidance, it employs a twostage training to enhance controllability and structural consistency, a

Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting

Published:3/21/2025

Dynamic Scene ReconstructionGaussian Motion NetworkInstant Streaming FrameworkKey-frame-guided Reconstruction StrategyMulti-View Feature Projection

The Instant Gaussian Stream (IGS) framework addresses the high reconstruction time and error accumulation in dynamic scene FreeViewpoint Videos. It uses a generalized Anchordriven Gaussian Motion Network for rapid Gaussian motion generation and a keyframeguided strategy for i

4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Published:10/13/2023

4D Gaussian Splatting RepresentationDynamic Scene RenderingEfficient Neural Voxel EncodingReal-Time RenderingLightweight MLP

The paper introduces 4D Gaussian Splatting (4DGS) for dynamic scene rendering, integrating 3D Gaussians and 4D neural voxels. It achieves realtime performance at 82 FPS on an RTX 3090 GPU, maintaining superior rendering quality compared to stateoftheart methods.

1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering

Published:3/21/2025

4D Gaussian SplattingDynamic Scene ReconstructionStorage Optimization MethodsFast Rendering TechniquesHigh Frame Rate Rendering

The 4DGS1K framework improves 4D Gaussian Splatting by using a SpatialTemporal Variation Score and Temporal Filter, achieving over 1000 FPS rendering speed, reducing storage by 41x, while maintaining visual quality.

3D Gaussian Splatting for Real-Time Radiance Field Rendering

Published:8/8/2023

3D Gaussian Splatting RepresentationReal-Time Radiance Field RenderingVisual Quality OptimizationVolumetric Scene RenderingSparse Point Scene Representation

The paper presents a 3D Gaussian splatting method for realtime radiance field rendering, introducing three key components: Gaussian scene representation, anisotropic covariance density optimization, and a fast visibilityaware rendering algorithm, achieving ≥30 fps at 1080p reso

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Published:3/6/2024

High-Resolution Image SynthesisImproved Diffusion Modeling TechniquesText-to-Image GenerationBidirectional Information Flow ArchitectureNoise Sampling Technique Optimization

This study introduces a novel multimodal diffusion Transformer (MMDiT) architecture that utilizes rectified flow for enhanced highresolution image synthesis. Optimized noise sampling and bidirectional information flow improve text comprehension and user preference ratings, vali

iAgent: LLM Agent as a Shield between User and Recommender Systems

Published:2/20/2025

User-Agent MechanismRecommender System SecurityLLM AgentAlgorithmic Bias MitigationPersonalized Recommendation Optimization

The paper introduces a useragentplatform paradigm with LLM agents as a protective shield, addressing vulnerabilities in traditional recommender systems. It develops the INSTRUCTREC dataset and the iAgent and i2Agent, with the latter showing a 16.6% improvement in personalizatio

Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields

Published:11/11/2025

High-Performance Procedural Grasp SynthesisContact Field Data StructureUnsupervised Grasp GenerationRapid Grasp Synthesis AlgorithmReal-time Grasp for Dexterous Hands

Lightning Grasp is introduced as a novel highperformance grasp synthesis algorithm that significantly speeds up grasp generation and enables unsupervised grasping of irregular and toollike objects. It leverages the Contact Field structure to decouple complex geometry from the s

Embracing Bulky Objects with Humanoid Robots: Whole-Body Manipulation with Reinforcement Learning

Published:9/17/2025

Reinforcement Learning for Whole-Body ManipulationHumanoid Robot Multi-Contact InteractionNeural Signed Distance Field RepresentationLarge-Scale Human Motion Data DistillationLong-Horizon Task Control

This paper introduces a reinforcement learning framework for humanoid robots to embrace bulky objects via wholebody manipulation. It combines human motion priors with neural signed distance fields to generate robust and natural motions, enhancing multicontact stability and adap

Leveraging BERT and TFIDF Features for Short Text Clustering via Alignment-Promoting Co-Training

Published:11/1/2024

BERT and TFIDF Co-Training ClusteringShort Text ClusteringFeature Alignment EnhancementDeep Representation LearningClustering Algorithm Evaluation

The COTC framework combines BERT and TFIDF features for enhanced short text clustering, achieving effective alignment through mutual learning of two modules. Experiments show significant performance improvements over stateoftheart methods on eight benchmark datasets.

RankMixer: Scaling Up Ranking Models in Industrial Recommenders

Published:7/21/2025

Hardware-Aware Recommendation SystemsMulti-Head Token Mixing ModuleSparse-MoE VariantFeature Interaction ArchitectureBillion-Parameter Model

RankMixer is a hardwareaware ranking model for industrial recommenders, overcoming cost and latency challenges. It employs a multihead token mixing module for enhanced efficiency and scalability, achieving significant user engagement gains with a billionparameter SparseMoE va

WHOLEBODYVLA: TOWARDS UNIFIED LATENT VLA FOR WHOLE-BODY LOCO-MANIPULATION CONTROL

Published:12/11/2025

Whole-Body Humanoid Robot ControlVision-Language-Action ModelRobotic Action LearningAction Learning from Low-Cost VideosLoco-Manipulation-Oriented Reinforcement Learning

This study presents , a unified latent visionlanguageaction framework enhancing humanoid robots' performance in locomanipulation tasks. It learns from lowcost egocentric videos and employs a tailored reinforcement learning policy, achieving a 21.3% performance b

HAC++: Towards 100X Compression of 3D Gaussian Splatting

Published:1/22/2025

3D Gaussian Splatting CompressionContext Modeling and Information CompressionAdaptive Quantization ModuleHigh-Fidelity Rendering AlgorithmSparse Point Cloud Compression

HAC introduces a novel compression framework leveraging unorganized anchors and structured hash grids for spatial context utilization, achieving over 100x size reduction while enhancing fidelity through precise probability estimation and entropy coding.

81 - 100 / 980

Papers