PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning

2025-03-13 · Yirong Sun, Yanjun Chen

We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core, PRISM adopts a 3D Point Cloud-Language Model (3D-PC-LLM) to mitigate occlusion and viewpoint biases, ensuring more stable and spatially consistent preference signals. Additionally, PRISM leverages Chain-of-Thought (CoT) reasoning to incorporate long-horizon considerations, thereby preventing the short-sighted feedback often seen in static preference comparisons. In contrast to conventional PBRL techniques, this integration of 3D perception and future-oriented reasoning leads to significant gains in preference agreement rates, faster policy convergence, and robust generalization across unseen robotic environments. Our empirical results, spanning tasks such as robotic manipulation and autonomous navigation, highlight PRISM's potential for real-world applications where precise spatial understanding and reliable long-term decision-making are critical. By bridging 3D geometric awareness with CoT-driven preference modeling, PRISM establishes a comprehensive foundation for scalable, human-aligned reinforcement learning.

📄 PDF Abstract BibTeX arXiv:2503.10177

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous NavigationDecision MakingLanguage ModelingLanguage Modelling reinforcement-learning Reinforcement Learning

PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs

2026-05-07 · Trimble Chang, Yihang Liu, Mingjing Han, Han Zhang arxiv

Dynamic text-attributed graphs (DyTAGs) provide a powerful framework for modeling evolving systems in which node semantics and time-dependent interactions are tightly coupled. Recently, multimodal learning has emerged as…

Representation Learning Link Prediction

Drift: Decoding-time Personalized Alignments with Implicit User Preferences

2025-02-20 · Minbeom Kim, Kang-il Lee, Seongho Joo, Hwaran Lee 외

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. T…

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection

2025-07-11 · Mahdiyar Molahasani, Azadeh Motamedi, Michael Greenspan, Il-Min Kim 외 arxiv

We introduce Projection-based Reduction of Implicit Spurious bias in vision-language Models (PRISM), a new data-free and task-agnostic solution for bias mitigation in VLMs like CLIP. VLMs often inherit and amplify biases…

PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur

2026-07-04 · Gopi Raju Matta, Reddypalli Trisha, Vemunuri Divya Madhuri, Kaushik Mitra arxiv

We address the inverse problem of blind 3D scene reconstruction from extremely motion-blurred images, a scenario where traditional Structure-from-Motion (SfM) pipelines fail. Existing approaches typically circumvent this…

PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment

2026-06-30 · Aymeric Fleith, Julian Zirbel, Daniel Cremers, Niclas Zeller arxiv

We introduce PRISM-VO, a novel pure optimization-based sparse photometric visual odometry framework for focused plenoptic cameras. The core of PRISM-VO is a novel photometric plenoptic bundle adjustment which jointly opt…

Visual Odometry