Copertina

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Seo Hyun, Park, Jin Bok, Koo, Do Yeon, Park, Hogun, Chun, Il Yong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MAMS: Model-Agnostic Module Selection Framework for Video Captioning
di: Lee, Sangho, et al.
Pubblicazione: (2025)

Autoregression-free video prediction using diffusion model for mitigating error propagation
di: Ko, Woonho, et al.
Pubblicazione: (2025)

TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving
di: Gorgulu, Tugrul, et al.
Pubblicazione: (2026)

Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
di: Jung, Heesoo, et al.
Pubblicazione: (2025)

Low-pass Personalized Subgraph Federated Recommendation
di: Sim, Wooseok, et al.
Pubblicazione: (2026)

Curriculum Guided Personalized Subgraph Federated Learning
di: Kang, Minku, et al.
Pubblicazione: (2025)

Self-supervised Adversarial Purification for Graph Neural Networks
di: Lee, Woohyun, et al.
Pubblicazione: (2026)

Enhancing Knowledge Tracing with Concept Map and Response Disentanglement
di: Park, Soonwook, et al.
Pubblicazione: (2024)

CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoders
di: Park, Jongwon, et al.
Pubblicazione: (2025)

Combating the effects of speed and delays in end-to-end self-driving
di: Tampuu, Ardi, et al.
Pubblicazione: (2023)

Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection
di: Kim, Youbin, et al.
Pubblicazione: (2026)

VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis
di: Park, Jinho, et al.
Pubblicazione: (2026)

Hierarchical end-to-end autonomous navigation through few-shot waypoint detection
di: Ghafourian, Amin, et al.
Pubblicazione: (2024)

End-to-End Driving via Self-Supervised Imitation Learning Using Camera and LiDAR Data
di: Park, Jin Bok, et al.
Pubblicazione: (2023)

Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation
di: Jeong, Jiwon, et al.
Pubblicazione: (2025)

UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
di: Kang, Hyunju, et al.
Pubblicazione: (2026)

Modality-Augmented Fine-Tuning of Foundation Robot Policies for Cross-Embodiment Manipulation on GR1 and G1
di: Park, Junsung, et al.
Pubblicazione: (2025)

Towards grounded autonomous research: an end-to-end LLM mini research loop on published computational physics
di: Huang, Haonan
Pubblicazione: (2026)

New Record of Ixodes columnae , Detached From a Human in the Republic of Korea
di: Jin Seo Park, et al.
Pubblicazione: (2026)

Memory-efficient deep end-to-end posterior network (DEEPEN) for inverse problems
di: Chand, Jyothi Rikhab, et al.
Pubblicazione: (2024)

METDrive: Multi-modal End-to-end Autonomous Driving with Temporal Guidance
di: Guo, Ziang, et al.
Pubblicazione: (2024)

Deep-learning-driven end-to-end metalens imaging
di: Seo, Joonhyuk, et al.
Pubblicazione: (2023)

Hierarchical nitrogen‐doped multichannel carbon nanofibers for efficient potassium–selenium batteries
di: Jae Bong Lim, et al.
Pubblicazione: (2025)

Better Sampling, towards Better End-to-end Small Object Detection
di: Huang, Zile, et al.
Pubblicazione: (2024)

Materealize: a multi-agent deliberation system for end-to-end material design and synthesis
di: Kim, Seongmin, et al.
Pubblicazione: (2026)

Power-efficiency trade-off for finite-time quantum harmonic Otto heat engine via phase-space approach
di: Chun, Hyun-Myung, et al.
Pubblicazione: (2025)

EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance
di: Suh, Heejae, et al.
Pubblicazione: (2025)

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
di: Nassar, Ahmed, et al.
Pubblicazione: (2025)

Toward end-to-end quantum simulation for protein dynamics
di: Liu, Zhenning, et al.
Pubblicazione: (2024)

Federated Recommender System with Data Valuation for E-commerce Platform
di: Park, Jongwon, et al.
Pubblicazione: (2025)

End-to-end differentiable network traffic simulation with dynamic route choice
di: Seo, Toru
Pubblicazione: (2026)

Toward end-to-end quantum simulation of rapidly distorted turbulence
di: Meng, Zhaoyuan, et al.
Pubblicazione: (2025)

End-to-end autonomous scientific discovery on a real optical platform
di: Yang, Shuxing, et al.
Pubblicazione: (2026)

Implicit 3D scene reconstruction using deep learning towards efficient collision understanding in autonomous driving
di: Ramanayake, Akarshani, et al.
Pubblicazione: (2025)

AudioGenX: Explainability on Text-to-Audio Generative Models
di: Kang, Hyunju, et al.
Pubblicazione: (2025)

Improving Multi-hop Logical Reasoning in Knowledge Graphs with Context-Aware Query Representation Learning
di: Kim, Jeonghoon, et al.
Pubblicazione: (2024)

JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA
di: Kang, Hyunju, et al.
Pubblicazione: (2026)

An efficient end-to-end computational framework for the generation of ECG calibrated volumetric models of human atrial electrophysiology
di: Zappon, Elena, et al.
Pubblicazione: (2025)

Evaluation of green kiwifruit juice extract on physicochemical properties, antioxidant activity, and tenderness of beef M. semitendinosus with in vitro digestion
di: Haeun Kim, et al.
Pubblicazione: (2024)

An experimentally validated end-to-end framework for operando modeling of intrinsically complex metallosilicates
di: Jung, Jong Hyun, et al.
Pubblicazione: (2025)