Imagen de Portada

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhi, Hongyan, Chen, Peihao, Li, Junyan, Ma, Shuailei, Sun, Xinyu, Xiang, Tianhang, Lei, Yinjie, Tan, Mingkui, Gan, Chuang
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
por: Zhi, Hongyan, et al.
Publicado: (2025)

MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
por: Hong, Yining, et al.
Publicado: (2024)

CoNav: A Benchmark for Human-Centered Collaborative Navigation
por: Li, Changhao, et al.
Publicado: (2024)

MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modeling
por: Huang, Diwei, et al.
Publicado: (2024)

Steering LLM Thinking with Budget Guidance
por: Li, Junyan, et al.
Publicado: (2025)

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
por: Yang, Yuncong, et al.
Publicado: (2024)

SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-world Object Detector
por: Ma, Shuailei, et al.
Publicado: (2023)

FlowCompile: An Optimizing Compiler for Structured LLM Workflows
por: Li, Junyan, et al.
Publicado: (2026)

FlexAttention for Efficient High-Resolution Vision-Language Models
por: Li, Junyan, et al.
Publicado: (2024)

Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
por: Khandelwal, Naitik, et al.
Publicado: (2023)

Understanding Emotional Body Expressions via Large Language Models
por: Lu, Haifeng, et al.
Publicado: (2024)

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
por: Wang, Yinjie, et al.
Publicado: (2025)

Disentangled Acoustic Fields For Multimodal Physical Scene Understanding
por: Yin, Jie, et al.
Publicado: (2024)

Deformation-based In-Context Learning for Point Cloud Understanding
por: Lin, Chengxing, et al.
Publicado: (2026)

UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception
por: Chen, Chuang, et al.
Publicado: (2024)

LLM4AMC: Adapting Large Language Models for Adaptive Modulation and Coding
por: Pan, Xinyu, et al.
Publicado: (2025)

LLM4XCE: Large Language Models for Extremely Large-Scale Massive MIMO Channel Estimation
por: Li, Renbin, et al.
Publicado: (2025)

Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs
por: Hsu, Hao-Yu, et al.
Publicado: (2026)

A Novel Access Control and Privacy-Enhancing Approach for Models in Edge Computing
por: Li, Peihao
Publicado: (2024)

EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
por: Cai, Han, et al.
Publicado: (2022)

Learning 3D Persistent Embodied World Models
por: Zhou, Siyuan, et al.
Publicado: (2025)

Beyond the Surface: Measuring Self-Preference in LLM Judgments
por: Chen, Zhi-Yuan, et al.
Publicado: (2025)

HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
por: Dong, Jiangwen, et al.
Publicado: (2025)

Mixed Attention Transformer Enhanced Channel Estimation for Extremely Large-Scale MIMO Systems
por: Li, Shuang shuang, et al.
Publicado: (2024)

Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
por: Wu, Di, et al.
Publicado: (2025)

GANPrompt: Enhancing Robustness in LLM-Based Recommendations with GAN-Enhanced Diversity Prompts
por: Li, Xinyu, et al.
Publicado: (2024)

VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
por: Ngo, Tuan Duc, et al.
Publicado: (2026)

Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
por: Kong, Lingdong, et al.
Publicado: (2024)

Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
por: Fu, Rao, et al.
Publicado: (2024)

UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective
por: He, Jun, et al.
Publicado: (2025)

Scenario Understanding of Traffic Scenes Through Large Visual Language Models
por: Rivera, Esteban, et al.
Publicado: (2025)

Adaptive Masking Enhances Visual Grounding
por: Jia, Sen, et al.
Publicado: (2024)

PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement
por: Wang, Yian, et al.
Publicado: (2026)

VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes
por: Wu, Ke, et al.
Publicado: (2025)

Decoupled Prototype Learning for Reliable Test-Time Adaptation
por: Wang, Guowei, et al.
Publicado: (2024)

SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding
por: Xu, Pengxin, et al.
Publicado: (2026)

Can Large Language Models Understand Preferences in Personalized Recommendation?
por: Tan, Zhaoxuan, et al.
Publicado: (2025)

TextPSG: Panoptic Scene Graph Generation from Textual Descriptions
por: Zhao, Chengyang, et al.
Publicado: (2023)

NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
por: Xu, Wei, et al.
Publicado: (2025)

Real-Time Load Estimation for Load-lifting Exoskeletons Using Insole Pressure Sensors and Machine Learning
por: Wu, Kaida, et al.
Publicado: (2025)