Copertina

Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nguyen, Huy-Dung, Bairouk, Anass, Maras, Mirjana, Xiao, Wei, Wang, Tsun-Hsuan, Chareyre, Patrick, Hasani, Ramin, Blanchon, Marc, Rus, Daniela
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencoder
di: Bairouk, Anass, et al.
Pubblicazione: (2024)

Optical Flow Matters: an Empirical Comparative Study on Fusing Monocular Extracted Modalities for Better Steering
di: Makiyeh, Fouad, et al.
Pubblicazione: (2024)

Enhancing Steering Estimation with Semantic-Aware GNNs
di: Makiyeh, Fouad, et al.
Pubblicazione: (2025)

Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications
di: Du, Yao, et al.
Pubblicazione: (2024)

Text-to-Drive: Diverse Driving Behavior Synthesis via Large Language Models
di: Nguyen, Phat, et al.
Pubblicazione: (2024)

Towards Cooperative Flight Control Using Visual-Attention
di: Yin, Lianhao, et al.
Pubblicazione: (2022)

Adaptive Control in Autonomous Driving via Real-Time Recurrent RL
di: Lemmel, Julian, et al.
Pubblicazione: (2026)

ABNet: Attention BarrierNet for Safe and Scalable Robot Learning
di: Xiao, Wei, et al.
Pubblicazione: (2024)

Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
di: Farsang, Mónika, et al.
Pubblicazione: (2025)

Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification
di: Farsang, Mónika, et al.
Pubblicazione: (2026)

Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?
di: Farsang, Mónika, et al.
Pubblicazione: (2023)

See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection
di: Mallak, Amir, et al.
Pubblicazione: (2026)

Probing Multimodal LLMs as World Models for Driving
di: Sreeram, Shiva, et al.
Pubblicazione: (2024)

Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks
di: Quach, Alex, et al.
Pubblicazione: (2024)

Holistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models
di: Wu, Haoyang, et al.
Pubblicazione: (2025)

Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features
di: Chahine, Makram, et al.
Pubblicazione: (2024)

Paysage absolu (sur C.F. Ramuz)
di: Alain Chareyre-Méjan
Pubblicazione: (1998)

ReGen: Generative Robot Simulation via Inverse Design
di: Nguyen, Phat, et al.
Pubblicazione: (2025)

Efficient Image Synthesis with Sphere Latent Encoder
di: Do, Tung, et al.
Pubblicazione: (2026)

RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval
di: Nguyen, Long, et al.
Pubblicazione: (2025)

Normal viscosity and Viscous resuspension of non-Brownian suspensions
di: Chèvremont, William, et al.
Pubblicazione: (2021)

Efficient Rhodamine B removal by photocatalysis using polyacrylonitrile/Ag2S nanofibers prepared by combining electrospinning technology and facile gas–solid reaction
di: Vu Dinh Thao, et al.
Pubblicazione: (2024)

Epistemologies and Aesthetics of Curriculum, Pedagogical Praxis and Assessment in the Visual Arts: A Comparative Analysis of the International Baccalaureate Diploma Programme and the New South Wales Stage 6 Visual Arts Syllabus
di: Fiona Blaikie, et al.
Pubblicazione: (2024)

Unconsented Sensing: A Sociotechnical Governance Framework for 6G ISAC
di: Sedrati, Anass
Pubblicazione: (2026)

Rigidity results with curvature conditions from Lichnerowicz Laplacian and applications
di: Cho, Gunhee, et al.
Pubblicazione: (2021)

R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models
di: Nguyen, Viet Dung, et al.
Pubblicazione: (2024)

MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration
di: Armeniakos, Giorgos, et al.
Pubblicazione: (2025)

Experimental studies on torsional behavior of reinforced concrete beams strengthened using hybrid carbon and basalt FRP sheets
di: Vinh Sang Nguyen, et al.
Pubblicazione: (2025)

SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving
di: Huynh, Minh Tri, et al.
Pubblicazione: (2024)

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
di: Ma, Pingchuan, et al.
Pubblicazione: (2024)

Latent Abstraction for Retrieval-Augmented Generation
di: T, Ha Lan N., et al.
Pubblicazione: (2026)

TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving
di: Che, Quang-Huy, et al.
Pubblicazione: (2024)

Examining the Relationship Between Daily Activity Levels and Elder Abuse and Neglect: Bringing Light on Elder Abuse
di: Gül Bülbül Maraş, et al.
Pubblicazione: (2025)

Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder
di: Nguyen, Duy A., et al.
Pubblicazione: (2023)

A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inference
di: Nguyen, Duc Hau, et al.
Pubblicazione: (2025)

Tacrolimus‐Related Hepatic Sinusoidal Obstruction Syndrome in a Case Receiving Deceased Liver Donor Liver Transplantation
di: Yu‐Tsun Hsieh, et al.
Pubblicazione: (2025)

Universal separable structure of the optical potential
di: Arellano, H. F., et al.
Pubblicazione: (2024)

Microscopic bell-shape nonlocality: the case of proton scattering off $^{40}$Ca at 200 MeV
di: Blanchon, G., et al.
Pubblicazione: (2024)

Revisiting the Disequilibrium Issues in Tackling Heart Disease Classification Tasks
di: Hoang, Thao, et al.
Pubblicazione: (2024)

A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives
di: Nguyen, Ti Ti, et al.
Pubblicazione: (2025)