Cover Image

RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Waite, Joshua R., Hasan, Md. Zahid, Liu, Qisai, Jiang, Zhanhong, Hegde, Chinmay, Sarkar, Soumik
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing PPO with Trajectory-Aware Hybrid Policies
by: Liu, Qisai, et al.
Published: (2025)

COOPO: Cyclic Offline-Online Policy Optimization Algorithm
by: Liu, Qisai, et al.
Published: (2026)

Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion
by: Liu, Qisai, et al.
Published: (2025)

FUSE: First-Order and Second-Order Unified SynthEsis in Stochastic Optimization
by: Jiang, Zhanhong, et al.
Published: (2025)

DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models
by: Saadati, Nastaran, et al.
Published: (2025)

Lighting-aware Unified Model for Instance Segmentation
by: Liu, Qisai, et al.
Published: (2026)

DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models
by: Saadati, Nastaran, et al.
Published: (2024)

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos
by: Hasan, Md Zahid, et al.
Published: (2023)

Balancing Utility and Privacy: Dynamically Private SGD with Random Projection
by: Jiang, Zhanhong, et al.
Published: (2025)

LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy
by: Yang, Hsin-Jung, et al.
Published: (2026)

ADKO: Agentic Decentralized Knowledge Optimization
by: Rillo, Lucas Nerone, et al.
Published: (2026)

Incorporating System-level Safety Requirements in Perception Models via Reinforcement Learning
by: Fan, Weisi, et al.
Published: (2024)

TabQL: In-Context Q-Learning with Tabular Foundation Models
by: Liu, Qisai, et al.
Published: (2026)

STITCH: Surface reconstrucTion using Implicit neural representations with Topology Constraints and persistent Homology
by: Jignasu, Anushrut, et al.
Published: (2024)

Decentralized Relaxed Smooth Optimization with Gradient Descent Methods
by: Jiang, Zhanhong, et al.
Published: (2025)

Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
by: Koirala, Prajwal, et al.
Published: (2024)

FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning
by: Koirala, Prajwal, et al.
Published: (2024)

GENESIS-RL: GEnerating Natural Edge-cases with Systematic Integration of Safety considerations and Reinforcement Learning
by: Yang, Hsin-Jung, et al.
Published: (2024)

FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
by: Luo, Haozheng, et al.
Published: (2026)

WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
by: Feuer, Benjamin, et al.
Published: (2025)

Data-driven Kinematic Modeling in Soft Robots: System Identification and Uncertainty Quantification
by: Jiang, Zhanhong, et al.
Published: (2025)

Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree
by: Khosravi, Mahsa, et al.
Published: (2025)

Neural CDEs as Correctors for Learned Time Series Models
by: Shahid, Muhammad Bilal, et al.
Published: (2025)

Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries
by: Rabeh, Ali, et al.
Published: (2024)

Leveraging Vision Language Models for Specialized Agricultural Tasks
by: Arshad, Muhammad Arbab, et al.
Published: (2024)

Asynchronous Training Schemes in Distributed Learning with Time Delay
by: Wang, Haoxiang, et al.
Published: (2022)

SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data
by: Ogezi, Michael, et al.
Published: (2025)

Reinforcement Learning for Autonomous Point-to-Point UAV Navigation
by: Oyinlola, Salim, et al.
Published: (2025)

MARVIS: Modality Adaptive Reasoning over VISualizations
by: Feuer, Benjamin, et al.
Published: (2025)

Driving as a Diagnostic Tool: Scenario-based Cognitive Assessment in Older Drivers from Driving Video
by: Hasan, Md Zahid, et al.
Published: (2025)

Decorum: A Language-Based Approach For Style-Conditioned Synthesis of Indoor 3D Scenes
by: Marshall, Kelly O., et al.
Published: (2025)

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
by: Liu, Yang, et al.
Published: (2025)

Enhancing Vision-Language Models for Autonomous Driving through Task-Specific Prompting and Spatial Reasoning
by: Wu, Aodi, et al.
Published: (2025)

BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity
by: Yang, Chih-Hsuan, et al.
Published: (2024)

Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing
by: Nirala, A K, et al.
Published: (2023)

NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving
by: Tian, Kexin, et al.
Published: (2025)

Autonomous Crack Detection using Deep Learning on Synthetic Thermogram Datasets
by: Pimpalkhare, Chinmay Makarand, et al.
Published: (2024)

SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
by: Long, Yancheng, et al.
Published: (2026)

Distributed Direct Preference Optimization
by: Jiang, Zhanhong
Published: (2026)

Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
by: Lian, Shijie, et al.
Published: (2025)